© 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. 8036
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations, especially mountains or fountains

    oai_token-act-pair · gpt-3.5-turbo

    terms related to counting or measurement

    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
     mature
    -0.62
     puberty
    -0.61
     tongue
    -0.61
     professionally
    -0.60
     chemically
    -0.60
     Decay
    -0.58
     psychotic
    -0.58
     frame
    -0.58
     Psych
    -0.57
     commercially
    -0.56
    POSITIVE LOGITS
    ount
    4.64
    OUNT
    1.68
    ounty
    1.45
    ounter
    1.40
    OUN
    1.38
    ountain
    1.12
    mount
    1.12
    ont
    1.08
    auc
    0.96
    onder
    0.96
    Activations Density 0.021%

    No Known Activations