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

    Neuronpedia

    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. 7-RES-JB
    11. 3071
    Prev
    Next
    INDEX
    Explanations

    phrases related to prediction or expectation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dunno
    -0.67
     Goldberg
    -0.60
    */(
    -0.59
     Photograph
    -0.58
     supposedly
    -0.56
     *)
    -0.56
     ostensibly
    -0.55
     zones
    -0.55
    Downloadha
    -0.55
    oros
    -0.54
    POSITIVE LOGITS
     someday
    1.08
     continue
    0.99
     hereafter
    0.97
     future
    0.95
     tomorrow
    0.92
     revisit
    0.86
    future
    0.83
     revis
    0.83
    contin
    0.82
     soon
    0.81
    Activations Density 0.894%

    No Known Activations