© 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. 18730
    Prev
    Next
    INDEX
    Explanations

    phrases related to overall evaluation or sentiment

    oai_token-act-pair · gpt-3.5-turbo

    overall sentiments and evaluations related to performance or quality

    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
     vou
    -0.75
    hots
    -0.68
    ggles
    -0.66
    oola
    -0.64
    etus
    -0.64
    eele
    -0.63
    saf
    -0.62
     fortun
    -0.61
    agara
    -0.61
    ãĥĥãĥĪ
    -0.60
    POSITIVE LOGITS
    endif
    0.68
     Delete
    0.68
     Walk
    0.60
     Default
    0.60
     Journals
    0.59
    ONSORED
    0.57
     Related
    0.57
    APTER
    0.56
     Orlando
    0.56
     Also
    0.56
    Activations Density 0.244%

    No Known Activations