© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    references to something that is not new

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "newness."

    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
    ignt
    -0.76
    ++++
    -0.73
     PRESS
    -0.69
     teasp
    -0.65
     Bastard
    -0.64
    everal
    -0.63
     sqor
    -0.62
    ++++++++
    -0.59
    verning
    -0.58
     Brach
    -0.57
    POSITIVE LOGITS
    bie
    1.04
    bies
    0.82
    yk
    0.75
     phenomenon
    0.75
    hart
    0.73
     Zealand
    0.72
    owan
    0.71
    actionDate
    0.71
    aeus
    0.71
    Reilly
    0.71
    Activations Density 0.075%

    No Known Activations