© 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. 8-RES-JB
    11. 22520
    Prev
    Next
    INDEX
    Explanations

    the word "mod" with varying degrees of strength

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "mod" and related terms associated with moderation or modification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vana
    -0.75
    ibaba
    -0.71
    jriwal
    -0.65
    ï¸
    -0.64
    ©¶æ
    -0.63
    ISA
    -0.61
     Flavoring
    -0.61
    Enlarge
    -0.60
    mble
    -0.60
    Adapt
    -0.59
    POSITIVE LOGITS
    erella
    0.75
    opol
    0.72
    ooth
    0.65
    ighters
    0.65
    ail
    0.61
    oin
    0.61
    ruck
    0.60
    asty
    0.60
    nant
    0.59
    ude
    0.58
    Activations Density 0.158%

    No Known Activations