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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1985
    Prev
    Next
    INDEX
    Explanations

    references to spatial relationships involving the subject 'him' or 'them'

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and groups in relation to positions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ©ãĥ³
    -0.80
     Geek
    -0.70
    -)
    -0.69
    fact
    -0.69
    ãĥĭ
    -0.66
    inctions
    -0.65
    ammy
    -0.65
    Psy
    -0.64
    ociate
    -0.62
    itialized
    -0.61
    POSITIVE LOGITS
    atic
    0.83
     conduc
    0.82
    atics
    0.81
     selves
    0.77
    alian
    0.76
     tremend
    0.69
     dracon
    0.69
     unbeat
    0.68
     contemporaries
    0.67
    andering
    0.66
    Activations Density 0.177%

    No Known Activations