© 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. 21429
    Prev
    Next
    INDEX
    Explanations

    reasons or justifications

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the reason for" in various 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
    OLOGY
    -0.87
    chn
    -0.84
     ILCS
    -0.79
    ologue
    -0.77
    ngth
    -0.73
    Laughs
    -0.73
    busters
    -0.71
    acles
    -0.69
    tle
    -0.69
    eki
    -0.68
    POSITIVE LOGITS
     why
    1.39
     preferring
    1.33
     wanting
    1.21
     choosing
    1.20
     excluding
    1.16
     rejecting
    1.11
     believing
    1.09
     hating
    1.09
     abandoning
    1.05
     recommending
    1.05
    Activations Density 0.067%

    No Known Activations