© 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. 15163
    Prev
    Next
    INDEX
    Explanations

    information related to numerical rankings and statistics

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical rankings or statistics associated with various subjects

    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
    lique
    -0.81
    omething
    -0.78
    xual
    -0.78
    ¬¼
    -0.75
    ĪĴ
    -0.74
    ĺħ
    -0.72
    erent
    -0.71
    ²¾
    -0.69
    THING
    -0.68
    »Ĵ
    -0.68
    POSITIVE LOGITS
     surpass
    1.00
    behind
    0.95
     excluding
    0.86
     according
    0.82
     ranking
    0.80
     boasting
    0.79
     surpassed
    0.79
     comprising
    0.77
     ranked
    0.74
     EVER
    0.73
    Activations Density 0.369%

    No Known Activations