© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    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
     choke
    -0.84
     imaginable
    -0.81
     choking
    -0.80
    isable
    -0.79
     fade
    -0.78
     downt
    -0.77
     desper
    -0.75
     awake
    -0.75
     inconsistency
    -0.75
     revol
    -0.74
    POSITIVE LOGITS
     Its
    1.16
     Additionally
    1.05
     Named
    1.05
     It
    1.04
     According
    1.03
     Originally
    1.01
     Interestingly
    1.01
     Together
    1.00
     However
    1.00
     Previously
    1.00
    Activations Density 0.460%

    No Known Activations