Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16123
    Prev
    Next
    INDEX
    Explanations

    quotes or statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    citations or quotes from individuals in the text

    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
    olit
    -0.64
    light
    -0.62
    catch
    -0.61
    ~~~~~~~~
    -0.60
    olds
    -0.59
    rings
    -0.57
    regular
    -0.56
    together
    -0.56
    suits
    -0.56
    BOX
    -0.56
    POSITIVE LOGITS
     saying
    1.38
     Saying
    1.16
     stating
    1.00
     SAY
    0.98
     remark
    0.97
     telling
    0.96
     describing
    0.88
     suggesting
    0.87
     citing
    0.86
     noting
    0.85
    Activations Density 0.124%

    No Known Activations