© 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. 8-RES-JB
    11. 18528
    Prev
    Next
    INDEX
    Explanations

    mentions of specific time spans or durations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "year" and its variations indicating time duration

    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
    acted
    -0.68
    liction
    -0.66
    inite
    -0.65
    ahime
    -0.64
    =/
    -0.62
     ACTIONS
    -0.62
    eret
    -0.60
    lict
    -0.59
    eton
    -0.58
    emale
    -0.57
    POSITIVE LOGITS
     ago
    1.61
     Ago
    1.27
     ahead
    0.94
     later
    0.85
     apart
    0.84
     Later
    0.80
     overdue
    0.78
     earlier
    0.77
     away
    0.76
     prior
    0.75
    Activations Density 0.088%

    No Known Activations