© 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. 8-RES-JB
    11. 195
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    references to sequels or continuations of series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notor
    -0.66
     redes
    -0.65
     concess
    -0.55
     comr
    -0.55
     conduc
    -0.55
     conflic
    -0.55
    ikuman
    -0.54
    oqu
    -0.54
    compl
    -0.53
    xual
    -0.53
    POSITIVE LOGITS
    ↵
    0.90
     Anyway
    0.89
     ;)
    0.89
     !!
    0.88
    <|endoftext|>
    0.87
    ↵↵
    0.86
    ↵Âł
    0.86
    !:
    0.85
     :)
    0.84
    !!!
    0.83
    Activations Density 1.238%

    No Known Activations