Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9691
    Prev
    Next
    INDEX
    Explanations

    sentences with contrasting or opposing ideas

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or conclusions that emphasize a point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accomp
    -0.71
     defe
    -0.70
     unknown
    -0.66
     advis
    -0.66
     facult
    -0.65
     unanswered
    -0.63
     independ
    -0.63
     prohib
    -0.62
     estab
    -0.62
     uncertain
    -0.61
    POSITIVE LOGITS
     Rather
    1.88
     Instead
    1.66
    Rather
    1.54
     Quite
    1.40
     Nor
    1.39
    Instead
    1.38
     Nope
    1.31
     Neither
    1.13
    rather
    1.06
     It
    1.01
    Activations Density 0.291%

    No Known Activations