© 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. 9-RES-JB
    6. 1480
    Prev
    Next
    INDEX
    Explanations

    self-referential statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the "<|endoftext|>" token, indicating the end of a document or segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impunity
    -0.67
     substitutes
    -0.66
     intermedi
    -0.63
     aids
    -0.62
     excess
    -0.62
     offsets
    -0.61
     indistinguishable
    -0.61
     totality
    -0.60
     aides
    -0.60
     branches
    -0.59
    POSITIVE LOGITS
    stanbul
    1.31
    'm
    1.27
    've
    1.19
    EEE
    1.14
    ANS
    1.07
    nex
    1.05
     awoke
    1.04
    zzy
    1.03
     suppose
    0.98
    rina
    0.98
    Activations Density 0.185%

    No Known Activations