© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    financial figures or amounts expressed in currency

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and contract details in sports-related contexts

    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
     Wid
    -0.59
     WOM
    -0.59
     Study
    -0.59
     Concent
    -0.55
     Gallup
    -0.54
     poses
    -0.54
     symptom
    -0.54
    odor
    -0.52
     Stamp
    -0.52
     handwriting
    -0.52
    POSITIVE LOGITS
    million
    1.19
     million
    1.08
    billion
    0.94
    Ĥ
    0.86
     billion
    0.86
    ŃĶ
    0.85
     Million
    0.84
     lakh
    0.83
     Billion
    0.80
    illions
    0.77
    Activations Density 0.146%

    No Known Activations