© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    phrases indicating thoughts, beliefs, or hypotheses

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate speculation or belief

    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
    Merit
    -0.72
    anca
    -0.71
    EStreamFrame
    -0.68
    GMT
    -0.65
    ORPG
    -0.64
    Shipping
    -0.63
    acerb
    -0.63
    apeake
    -0.62
    \-
    -0.60
     PLUS
    -0.60
    POSITIVE LOGITS
    fully
    1.12
    lessly
    1.08
    istically
    0.95
     provoking
    0.86
    fulness
    0.86
    onymous
    0.84
    wise
    0.80
    inery
    0.74
    rison
    0.74
    stock
    0.74
    Activations Density 0.035%

    No Known Activations