© 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. 4-RES-JB
    11. 3681
    Prev
    Next
    INDEX
    Explanations

    words related to motor vehicles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to motor functions or mechanics

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

    No Comments

    Negative Logits
    pta
    -0.85
    ©¶æ
    -0.77
     Marketable
    -0.76
    holder
    -0.76
     WARN
    -0.73
    士
    -0.73
    çĶ°
    -0.69
    interstitial
    -0.69
     Anniversary
    -0.69
    ACTED
    -0.68
    POSITIVE LOGITS
    ility
    1.15
     mot
    1.03
    oly
    0.93
    oring
    0.93
    ör
    0.92
    olit
    0.90
    ocamp
    0.88
    urnal
    0.88
    sters
    0.86
    ory
    0.84
    Activations Density 0.009%

    No Known Activations