© 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. 2-RES-JB
    11. 1430
    Prev
    Next
    INDEX
    Explanations

    words related to conflict and surprise attacks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ambivalence and ambush scenarios

    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
     Occupations
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.73
    dom
    -0.72
    EVA
    -0.72
     Parenthood
    -0.69
    puff
    -0.67
    FUL
    -0.67
    MET
    -0.65
    SHIP
    -0.65
     AMERICA
    -0.65
    POSITIVE LOGITS
     amb
    1.13
    ushed
    1.06
    ience
    0.98
    iance
    0.96
    assad
    0.93
    agog
    0.90
    ivalent
    0.90
    ienced
    0.89
    iences
    0.88
    odox
    0.88
    Activations Density 0.002%

    No Known Activations