© 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. 6433
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a specific point or action

    oai_token-act-pair · gpt-3.5-turbo

    the word "what" in various contexts

    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
    robe
    -0.88
    ardless
    -0.74
    lich
    -0.67
    trop
    -0.64
    eer
    -0.63
    say
    -0.63
    ubs
    -0.62
    astical
    -0.62
    ways
    -0.61
    UNE
    -0.60
    POSITIVE LOGITS
     happens
    1.25
     happened
    1.21
     separates
    1.03
    soever
    1.02
     transpired
    0.96
     distinguishes
    0.89
     happ
    0.87
     motiv
    0.84
     Happ
    0.83
     bothers
    0.82
    Activations Density 0.060%

    No Known Activations