© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16534
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequence of events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athi
    -0.58
    cellent
    -0.56
    abul
    -0.55
    Anyone
    -0.54
    âĦ¢:
    -0.54
    interstitial
    -0.53
    aber
    -0.53
    ione
    -0.51
    hare
    -0.51
    []
    -0.50
    POSITIVE LOGITS
     then
    3.40
    then
    2.87
     THEN
    2.60
     Then
    2.24
    Then
    2.14
     thence
    1.51
     subsequently
    1.46
     thereafter
    1.28
     Afterwards
    1.24
     therefore
    1.22
    Activations Density 0.063%

    No Known Activations