© 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. 7-RES-JB
    11. 18650
    Prev
    Next
    INDEX
    Explanations

    names of groups, teams, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to teamwork and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     canal
    -0.69
     grap
    -0.63
     illeg
    -0.63
     cellul
    -0.63
    vasive
    -0.63
    Oracle
    -0.63
    Quantity
    -0.62
    romy
    -0.59
    GMT
    -0.59
     stalk
    -0.58
    POSITIVE LOGITS
    rollers
    0.91
    lishes
    0.77
     guiActiveUnfocused
    0.76
    akeru
    0.74
    hesion
    0.74
    agers
    0.68
    holders
    0.67
    isers
    0.67
    casters
    0.64
    legates
    0.62
    Activations Density 0.655%

    No Known Activations