© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    terms related to achievements or qualities of individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to influence, success, and authority in various contexts

    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
    olulu
    -0.74
     oneself
    -0.74
    orks
    -0.63
     ourselves
    -0.63
    $.
    -0.62
    amiya
    -0.60
    common
    -0.60
     Ga
    -0.59
    nant
    -0.58
    berra
    -0.58
    POSITIVE LOGITS
     differs
    0.95
     consisted
    0.93
     extends
    0.92
     consists
    0.87
     encompasses
    0.84
     woes
    0.83
     differed
    0.81
     revolves
    0.80
     shines
    0.78
     coincided
    0.78
    Activations Density 0.420%

    No Known Activations