© 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. 9-RES-JB
    11. 3585
    Prev
    Next
    INDEX
    Explanations

    phrases related to assisting or helping in a team context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individuals who contribute positively to a team or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mart
    -0.75
     solicitation
    -0.73
    pmwiki
    -0.69
     ISBN
    -0.68
    verend
    -0.66
     declass
    -0.66
    displayText
    -0.65
    respond
    -0.64
     Legisl
    -0.64
     loc
    -0.64
    POSITIVE LOGITS
     teammates
    1.06
     midfield
    1.00
     offensively
    0.98
     roster
    0.97
    team
    0.97
     defensively
    0.97
     teammate
    0.96
     offense
    0.90
     teams
    0.90
    league
    0.89
    Activations Density 0.300%

    No Known Activations