© 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. 18180
    Prev
    Next
    INDEX
    Explanations

    sensory and physical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    the character sequence "ľ" which appears to be a placeholder or encoding issue, suggesting a focus on special or unusual characters 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
     bun
    -0.80
     pellets
    -0.79
     mathemat
    -0.79
     teleport
    -0.77
     reflex
    -0.76
     ellipt
    -0.75
     vulner
    -0.75
     artif
    -0.74
     gymn
    -0.74
     supervised
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.10
    cffffcc
    1.10
    RELATED
    1.08
    AUT
    1.05
    Reason
    1.04
    Discuss
    1.03
    Reporting
    1.03
    ccording
    1.02
    License
    1.01
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.01
    Activations Density 0.110%

    No Known Activations