© 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. 2-RES-JB
    11. 17782
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or developments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.67
     Millions
    -0.63
     antioxid
    -0.62
     Solution
    -0.62
    projects
    -0.60
     Raise
    -0.60
     invocation
    -0.60
    edIn
    -0.59
    ledge
    -0.59
    wall
    -0.59
    POSITIVE LOGITS
    hers
    1.09
    nt
    0.99
    hes
    0.90
     definitely
    0.85
    wolves
    0.76
    ocument
    0.75
     certainly
    0.75
    wolf
    0.73
    Interstitial
    0.73
    omorphic
    0.73
    Activations Density 0.432%

    No Known Activations