© 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. 18746
    Prev
    Next
    INDEX
    Explanations

    adverbs or verbs indicating completion or continuation of past actions

    oai_token-act-pair · gpt-3.5-turbo

    words indicating prior occurrences or actions in the text

    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
     Kills
    -0.60
     Corpus
    -0.59
     Library
    -0.56
     Place
    -0.56
    Rush
    -0.55
     Sets
    -0.54
    OULD
    -0.54
     weap
    -0.54
     Digest
    -0.54
     preserves
    -0.54
    POSITIVE LOGITS
    been
    1.43
     begun
    1.40
     gotten
    1.40
     been
    1.40
     undergone
    1.36
     fallen
    1.24
     flown
    1.22
     risen
    1.20
     gone
    1.20
     taken
    1.18
    Activations Density 0.129%

    No Known Activations