© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4935
    Prev
    Next
    INDEX
    Explanations

    words related to fictional creatures or animals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ols
    -0.86
    ibaba
    -0.76
    ritz
    -0.72
     Schmidt
    -0.72
    yang
    -0.71
    AMA
    -0.71
     Roof
    -0.69
    dated
    -0.69
    enburg
    -0.68
    íķ
    -0.67
    POSITIVE LOGITS
     creatures
    3.21
     creature
    3.17
     Creatures
    2.43
     Creature
    2.19
     monsters
    1.63
     beasts
    1.61
     organisms
    1.54
     monster
    1.44
     beast
    1.41
     beings
    1.39
    Activations Density 0.027%

    No Known Activations