© 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. 13387
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions or sharing opinions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I'll" to indicate future intentions or actions

    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
     Hebdo
    -0.74
     Tactics
    -0.68
     Stability
    -0.60
    eele
    -0.60
    endez
    -0.58
     Result
    -0.58
     populations
    -0.56
    -+-+
    -0.55
     AVG
    -0.55
     Scores
    -0.54
    POSITIVE LOGITS
     myself
    0.80
    sorry
    0.74
    telling
    0.72
    ope
    0.71
     guessing
    0.71
    na
    0.71
    agree
    0.70
     glad
    0.70
    grim
    0.69
    ishi
    0.69
    Activations Density 0.085%

    No Known Activations