© 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. 24207
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or conditions involving a change or influence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to actions and behaviors that suggest social or political issues

    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
    ĸļ
    -0.70
     Duchess
    -0.68
     Museum
    -0.67
     Raider
    -0.63
     Twain
    -0.60
     Definitive
    -0.58
    姫
    -0.58
    tyard
    -0.58
     Sorceress
    -0.58
     Ll
    -0.58
    POSITIVE LOGITS
    aking
    0.89
    ogging
    0.88
    aring
    0.87
    reating
    0.87
    agging
    0.85
    aging
    0.85
    ipping
    0.84
    amping
    0.84
    icing
    0.83
    anging
    0.82
    Activations Density 0.449%

    No Known Activations