© 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. 2-RES-JB
    11. 4385
    Prev
    Next
    INDEX
    Explanations

    references to numerical values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number nine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    escription
    -0.85
    enture
    -0.81
    iated
    -0.78
    dayName
    -0.78
    REDACTED
    -0.75
     Lauder
    -0.75
    channelAvailability
    -0.75
    holders
    -0.74
    iating
    -0.72
    holder
    -0.71
    POSITIVE LOGITS
    999
    1.24
    9999
    1.23
    06
    1.15
    08
    1.10
    07
    1.09
    04
    1.07
    09
    1.04
    03
    1.04
    79
    1.01
    090
    1.01
    Activations Density 0.044%

    No Known Activations