© 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. 20196
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names starting with "Ger" and possibly followed by a specific pattern of letters

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ger" or variations of it

    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
    xual
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.69
     CPC
    -0.68
    netflix
    -0.67
    BOOK
    -0.65
     gulf
    -0.64
     Samoa
    -0.64
    eers
    -0.63
     favour
    -0.61
    uncture
    -0.61
    POSITIVE LOGITS
    rera
    1.05
    iatric
    1.03
    mination
    1.02
    bil
    1.02
    rit
    1.01
    anium
    1.00
    usalem
    0.97
    roth
    0.96
    ber
    0.94
    rod
    0.93
    Activations Density 0.019%

    No Known Activations