© 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. 7-RES-JB
    11. 13385
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and information about a complex subject or topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating complexity or lengthiness of a subject or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urchase
    -0.90
    Via
    -0.81
    UGH
    -0.80
    wife
    -0.80
    assad
    -0.78
    Happy
    -0.78
    thood
    -0.77
    venge
    -0.77
    Holy
    -0.75
    wives
    -0.74
    POSITIVE LOGITS
     fluct
    0.94
     hardly
    0.93
     loosely
    0.89
     overs
    0.85
     obsc
    0.82
     scarcely
    0.80
     unpredict
    0.80
     uneven
    0.79
     inconsistent
    0.79
     obfusc
    0.77
    Activations Density 0.569%

    No Known Activations