© 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. 15391
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and benefits or rewards offered in various contexts, possibly related to gaming or crowdfunding

    oai_token-act-pair · gpt-3.5-turbo

    elements related to coding and programming syntax

    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
     Ern
    -0.80
    edia
    -0.69
    chnology
    -0.67
    amen
    -0.67
     Juda
    -0.66
    lehem
    -0.65
    urgical
    -0.65
     public
    -0.65
    eenth
    -0.64
     nem
    -0.64
    POSITIVE LOGITS
     +
    1.89
    +
    1.78
     +#
    1.44
    +)
    1.42
    +.
    1.41
    +(
    1.40
     +=
    1.36
    +,
    1.34
     "+
    1.30
     ++
    1.30
    Activations Density 0.113%

    No Known Activations