© 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. 10-RES-JB
    11. 24015
    Prev
    Next
    INDEX
    Explanations

    short phrases related to various objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.75
    ophob
    -0.70
    views
    -0.68
    aura
    -0.68
    eye
    -0.67
    Accept
    -0.66
    Alpha
    -0.66
    iew
    -0.64
     Emails
    -0.62
    aos
    -0.61
    POSITIVE LOGITS
     precursor
    0.97
     fictional
    0.89
     subsidiary
    0.88
    hem
    0.87
     perennial
    0.86
     staple
    0.84
     mythical
    0.84
     fictitious
    0.83
     notoriously
    0.83
     predecessor
    0.81
    Activations Density 0.116%

    No Known Activations