© 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. 9997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or transition in focus or topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "In [context]" suggesting the introduction of new segments or topics

    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
    76561
    -0.70
    :/
    -0.68
    acid
    -0.68
     enthusi
    -0.63
     looms
    -0.62
     ®
    -0.62
     intimid
    -0.61
     constitu
    -0.61
     penet
    -0.60
     distur
    -0.59
    POSITIVE LOGITS
     addition
    1.26
    itialized
    1.21
    juries
    1.15
    cluded
    1.12
    jured
    1.12
     lieu
    1.12
     fact
    1.12
    mates
    1.12
     essence
    1.09
    cluding
    1.09
    Activations Density 0.151%

    No Known Activations