© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2255
    Prev
    Next
    INDEX
    Explanations

    words related to social media and communication platforms such as Twitter

    oai_token-act-pair · gpt-3.5-turbo
    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
     commissions
    -0.75
     favour
    -0.74
     edged
    -0.74
     accent
    -0.73
     territ
    -0.72
     furnished
    -0.70
     greenhouse
    -0.70
    chnology
    -0.70
     disadvantage
    -0.69
    POSITIVE LOGITS
    Dear
    1.51
    RIP
    1.50
    https
    1.47
    @
    1.45
    BRE
    1.38
    Twitter
    1.38
    Congratulations
    1.37
    Others
    1.37
    Thank
    1.37
    #
    1.35
    Activations Density 0.247%

    No Known Activations