© 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. 11-RES-JB
    11. 10009
    Prev
    Next
    INDEX
    Explanations

    technical details in a software or system context

    oai_token-act-pair · gpt-3.5-turbo

    details about technical features and capabilities of software or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chlor
    -0.78
    catentry
    -0.75
     vacated
    -0.72
     suffice
    -0.72
    */(
    -0.70
     scoff
    -0.69
    ryce
    -0.68
     ignor
    -0.68
    ashington
    -0.67
     thence
    -0.66
    POSITIVE LOGITS
     customizable
    1.21
     intuitive
    1.09
     Dozens
    1.07
     Supports
    1.03
     Beaut
    1.02
    Multiple
    1.02
    Beaut
    1.01
     Proced
    1.00
     Powerful
    1.00
    uitive
    0.99
    Activations Density 0.248%

    No Known Activations