© 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. 14264
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional work or operations

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to activities that involve groups or collaboration

    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
    athy
    -0.73
    henko
    -0.72
    croft
    -0.70
    ochond
    -0.69
    correct
    -0.69
    oola
    -0.67
    aun
    -0.66
    ombat
    -0.66
    icals
    -0.65
    zip
    -0.65
    POSITIVE LOGITS
    edIn
    0.66
     Crusade
    0.59
    river
    0.59
    TN
    0.58
    AME
    0.57
     professions
    0.56
     behalf
    0.56
     unconventional
    0.55
     fled
    0.55
     fictitious
    0.55
    Activations Density 0.194%

    No Known Activations