© 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. 10-RES-JB
    11. 23456
    Prev
    Next
    INDEX
    Explanations

    skills and actions related to various professions and tasks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and conjunctions in a wide range of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recent
    -0.62
    availability
    -0.62
    catentry
    -0.62
    mount
    -0.60
    ube
    -0.60
    ussie
    -0.60
    alm
    -0.59
    etermin
    -0.58
     Serving
    -0.58
    contact
    -0.58
    POSITIVE LOGITS
     gave
    1.48
     drove
    1.46
     proceeded
    1.46
     waited
    1.46
     ensured
    1.44
     threw
    1.43
     acted
    1.42
     took
    1.41
     stayed
    1.41
     blew
    1.40
    Activations Density 0.481%

    No Known Activations