© 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. 9-RES-JB
    11. 16258
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format (month, day, year)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overflowing
    -0.74
     dared
    -0.72
     sensitive
    -0.71
     drinkers
    -0.69
     hunted
    -0.68
     poisoning
    -0.68
     padd
    -0.68
     wor
    -0.68
     chained
    -0.66
     imprisoned
    -0.65
    POSITIVE LOGITS
     [+
    1.37
    5
    1.18
    0
    1.15
    09
    1.12
    06
    1.12
    08
    1.10
    05
    1.08
    00
    1.07
    8
    1.07
    02
    1.06
    Activations Density 0.081%

    No Known Activations