© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11829
    Prev
    Next
    INDEX
    Explanations

    locations or entities that have been subjects of news reports with specific actions tied to them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "had"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hammer
    -0.71
    bie
    -0.68
    bies
    -0.65
     Voters
    -0.64
    hack
    -0.63
    atin
    -0.60
    etting
    -0.57
    uating
    -0.57
     taxp
    -0.56
     Skies
    -0.56
    POSITIVE LOGITS
     been
    1.32
     undergone
    1.17
     begun
    1.11
     gone
    1.10
     gotten
    1.07
     become
    1.01
    iths
    1.00
     come
    0.90
    been
    0.89
     never
    0.88
    Activations Density 0.150%

    No Known Activations