© 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. 20506
    Prev
    Next
    INDEX
    Explanations

    phrases that may indicate dialogue

    oai_token-act-pair · gpt-3.5-turbo

    dialogue snippets that express uncertainty or lead to discussion

    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
    isans
    -0.69
     Burnett
    -0.67
     estranged
    -0.65
     redist
    -0.65
    ardless
    -0.64
     Abbott
    -0.63
    istry
    -0.63
     orchestr
    -0.63
     fres
    -0.63
     colleg
    -0.62
    POSITIVE LOGITS
    Chapter
    1.22
    Suddenly
    1.11
    Fuck
    1.05
    CHAPTER
    1.02
    Eventually
    1.00
    YES
    1.00
    [[
    0.96
    ³³³³
    0.93
    XXXX
    0.92
    Damn
    0.91
    Activations Density 0.215%

    No Known Activations