© 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. 7661
    Prev
    Next
    INDEX
    Explanations

    positive descriptive words and expressions

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptive phrases expressing positivity or critique

    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
    ãĥĺãĥ©
    -0.70
    anges
    -0.70
    adj
    -0.69
    opy
    -0.64
    _-
    -0.63
    ould
    -0.62
    =-=-=-=-=-=-=-=-
    -0.61
    OULD
    -0.61
    Domain
    -0.61
    annot
    -0.60
    POSITIVE LOGITS
     lately
    1.09
     fruitful
    1.00
     since
    0.99
     unsuccessful
    0.81
     successful
    0.79
     awhile
    0.78
     productive
    0.75
     steady
    0.74
     steadily
    0.72
    since
    0.72
    Activations Density 0.310%

    No Known Activations