© 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. 19731
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a result or intention

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "just so" and its variations

    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
    lees
    -0.76
    rees
    -0.68
    olor
    -0.68
    issance
    -0.67
    obs
    -0.67
    ighed
    -0.66
    NYSE
    -0.65
    bows
    -0.63
    chwitz
    -0.62
    û
    -0.61
    POSITIVE LOGITS
    iably
    0.71
    thodox
    0.64
    iator
    0.64
     fateful
    0.63
     plun
    0.60
    raz
    0.60
     decency
    0.60
     Voltage
    0.59
     ingred
    0.59
     dilig
    0.58
    Activations Density 0.044%

    No Known Activations