Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13293
    Prev
    Next
    INDEX
    Explanations

    names and locations related to the Middle East

    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
    211
    +0.09
    0.6%
    549
    +0.09
    0.6%
    669
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.09
    0.04
    549
    +0.09
    0.08
    442
    +0.08
    0.06
    Negative Logits
    代
    -0.61
    OME
    -0.51
    EMS
    -0.50
     Peb
    -0.49
    ĪĴ
    -0.48
    ancies
    -0.46
    orer
    -0.45
    OSP
    -0.45
     Dispatch
    -0.44
    CAST
    -0.44
    POSITIVE LOGITS
    riages
    0.75
    iously
    0.61
    ques
    0.60
    aneously
    0.59
    riott
    0.58
    quez
    0.58
    rying
    0.56
    zynski
    0.55
    iety
    0.52
    ious
    0.51
    Activations Density 9.929%

    No Known Activations