© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3968
    Prev
    Next
    INDEX
    Explanations

    negative descriptions or observations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "nothing."

    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
    fs
    -0.79
    orks
    -0.78
     Pastebin
    -0.71
     fixme
    -0.70
    rib
    -0.67
    imeters
    -0.66
    NAS
    -0.66
     Chains
    -0.66
    inders
    -0.65
    eds
    -0.63
    POSITIVE LOGITS
     missing
    0.90
     else
    0.84
     lurking
    0.83
     happening
    0.81
     poetic
    0.80
     buried
    0.78
     sinister
    0.78
     shameful
    0.77
     inherent
    0.76
     redeem
    0.75
    Activations Density 0.067%

    No Known Activations