© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13535
    Prev
    Next
    INDEX
    Explanations

    mentions of deep and ominous concepts or entities, particularly related to the idea of an abyss

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the "abyss" and demonic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verson
    -0.75
    ATURE
    -0.74
    pton
    -0.73
    ©¶æ
    -0.70
    kees
    -0.70
    ²
    -0.70
    Ĥ
    -0.69
    TRY
    -0.68
    akers
    -0.67
    BIL
    -0.66
    POSITIVE LOGITS
    inian
    0.85
     artific
    0.77
     legion
    0.76
     serpent
    0.76
     demons
    0.75
     conduit
    0.75
     abyss
    0.75
     gulf
    0.75
     destro
    0.75
     mund
    0.74
    Activations Density 0.053%

    No Known Activations