© 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. 0-RES-JB
    11. 16383
    Prev
    Next
    INDEX
    Explanations

    timestamps

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Last" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     endeav
    -0.69
     lay
    -0.66
    cker
    -0.65
     inclined
    -0.64
     oriented
    -0.63
    writing
    -0.62
     endowed
    -0.56
     readily
    -0.56
    gew
    -0.55
    formed
    -0.55
    POSITIVE LOGITS
     Last
    3.63
    Last
    2.45
     LAST
    2.20
    last
    1.91
     Yesterday
    1.69
     last
    1.63
     Earlier
    1.34
     Latest
    1.31
     Recently
    1.26
    Yesterday
    1.26
    Activations Density 0.011%

    No Known Activations