© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5672
    Prev
    Next
    INDEX
    Explanations

    terms related to financial markets, particularly hedge funds

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.21
    0.7%
    578
    +0.20
    0.7%
    524
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.13
    326
    +0.20
    0.09
    578
    +0.15
    0.04
    Negative Logits
    oke
    -1.08
    ional
    -1.02
    士
    -0.95
    AST
    -0.85
    eal
    -0.84
    ources
    -0.83
    OSE
    -0.82
    ONT
    -0.82
     Gutenberg
    -0.82
    ————————
    -0.81
    POSITIVE LOGITS
    hog
    2.06
     hedge
    1.33
    warts
    1.16
    keeper
    1.07
    chell
    1.06
    rament
    1.05
     Hedge
    1.05
    nut
    1.04
    wit
    1.03
    rosis
    1.01
    Activations Density 1.341%

    No Known Activations