© 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. 5033
    Prev
    Next
    INDEX
    Explanations

    links or URLs

    oai_token-act-pair · gpt-3.5-turbo

    elements related to social media or web URLs

    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
     monop
    -0.76
     HG
    -0.69
     Palest
    -0.66
     Fritz
    -0.64
     Fitz
    -0.64
     Austral
    -0.63
     BG
    -0.63
     princ
    -0.63
     Saras
    -0.63
     Lans
    -0.62
    POSITIVE LOGITS
    10000
    0.80
    2018
    0.77
    28
    0.76
    2019
    0.76
    18
    0.75
    254
    0.75
    Notice
    0.75
    508
    0.72
    58
    0.72
    201
    0.72
    Activations Density 0.089%

    No Known Activations