© 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. 8-RES-JB
    6. 9504
    Prev
    Next
    INDEX
    Explanations

    phrases related to timing or sequence, particularly the occurrence of an event after something else

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "after."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.79
    ãĤ¤ãĥĪ
    -0.76
    tick
    -0.74
    Tur
    -0.74
    isible
    -0.72
    ãĥ³ãĤ¸
    -0.72
    Scale
    -0.69
    alf
    -0.67
    ahime
    -0.67
    typ
    -0.67
    POSITIVE LOGITS
    math
    0.96
     completing
    0.94
     noticing
    0.94
    market
    0.93
     consulting
    0.92
     consultation
    0.89
     receiving
    0.88
     inspecting
    0.86
     obtaining
    0.84
     defeating
    0.84
    Activations Density 0.099%

    No Known Activations