© 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. 13499
    Prev
    Next
    INDEX
    Explanations

    Twitter URLs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 't' across various contexts

    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
    ĪĴ
    -0.93
     Decay
    -0.73
    ħĭ
    -0.68
     Zimmer
    -0.67
     Hitman
    -0.65
    Ĥİ
    -0.65
     Zamb
    -0.63
     MAC
    -0.62
     Phelps
    -0.62
     exha
    -0.62
    POSITIVE LOGITS
    asks
    1.14
    ruly
    1.07
    ricks
    1.05
    ribune
    1.04
    ournament
    1.01
    aked
    0.97
    unes
    0.96
    ickets
    0.94
    ribute
    0.94
    ripp
    0.93
    Activations Density 0.016%

    No Known Activations