© 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. 6-RES-JB
    11. 18769
    Prev
    Next
    INDEX
    Explanations

    statements of truth and facts

    oai_token-act-pair · gpt-3.5-turbo

    confirmations about the truth of statements or claims

    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
    ciating
    -0.82
     CLI
    -0.69
     mound
    -0.65
     activ
    -0.63
     thru
    -0.62
     brigade
    -0.62
     blender
    -0.61
     np
    -0.61
     mig
    -0.61
     chop
    -0.59
    POSITIVE LOGITS
    bnb
    0.69
     perverse
    0.69
    ptive
    0.69
     veiled
    0.69
    ptions
    0.67
    emis
    0.66
     paradox
    0.65
     Faust
    0.65
    adan
    0.65
    Mount
    0.64
    Activations Density 0.289%

    No Known Activations