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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 45971
    Prev
    Next
    INDEX
    Explanations

    information related to podcasts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.30
    1.3%
    326
    +0.14
    0.6%
    456
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.30
    0.07
    76
    +0.14
    0.09
    575
    +0.13
    0.13
    Negative Logits
    ju
    -0.75
    hog
    -0.74
    yer
    -0.74
    metics
    -0.72
    pes
    -0.68
    iage
    -0.68
    ple
    -0.68
     Bapt
    -0.67
    undai
    -0.66
    quez
    -0.66
    POSITIVE LOGITS
    odcast
    1.03
     podcasts
    0.98
     listeners
    0.95
     podcast
    0.89
    podcast
    0.88
     listener
    0.87
    CAST
    0.87
    itone
    0.86
    estern
    0.84
     Podcast
    0.84
    Activations Density 6.998%

    No Known Activations