Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2520
    Prev
    Next
    INDEX
    Explanations

    representatives or individuals associated with meetings or appointments

    oai_token-act-pair · gpt-3.5-turbo

    references to communication or interaction opportunities with public figures or representatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keeping
    -0.74
     toler
    -0.68
     overwrite
    -0.67
     modernization
    -0.67
     yearly
    -0.66
     limitation
    -0.65
     trapping
    -0.65
    mind
    -0.64
    Coming
    -0.64
     assumption
    -0.64
    POSITIVE LOGITS
     plaintiffs
    0.84
    amen
    0.79
     Mothers
    0.77
     heirs
    0.77
    axter
    0.75
     Virgin
    0.74
    oÄŁ
    0.73
     slain
    0.72
     representatives
    0.72
    kees
    0.72
    Activations Density 0.568%

    No Known Activations