© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 20365
    Prev
    Next
    INDEX
    Explanations

    terms related to mystical practices like witchcraft or sorcery

    oai_token-act-pair · gpt-3.5-turbo

    themes related to mysticism or supernatural beliefs

    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
    lander
    -0.64
     Entity
    -0.63
     DEC
    -0.62
    ForgeModLoader
    -0.61
     Seasons
    -0.60
     Energy
    -0.60
    ELF
    -0.60
    Delete
    -0.59
    DEF
    -0.59
     Expend
    -0.59
    POSITIVE LOGITS
    imental
    0.80
    psons
    0.76
    @
    0.75
    byter
    0.72
    ĻĤ
    0.69
    gap
    0.68
    oven
    0.68
    liest
    0.68
    .")
    0.67
    obook
    0.67
    Activations Density 0.000%

    No Known Activations