© 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. 9-RES-JB
    11. 16133
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the structure "but not."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve exceptions or limitations

    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
     Lear
    -0.68
     Puzzle
    -0.66
    oak
    -0.63
     cock
    -0.59
     Romeo
    -0.58
     chap
    -0.57
     wound
    -0.56
     passers
    -0.56
    leep
    -0.56
     Pic
    -0.56
    POSITIVE LOGITS
    undreds
    0.76
    partial
    0.68
    âĪ
    0.66
     entirety
    0.65
    osponsors
    0.64
    Absolutely
    0.64
    exclusive
    0.64
    %)
    0.63
    vari
    0.62
    idespread
    0.61
    Activations Density 0.145%

    No Known Activations