© 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. 11-RES-JB
    6. 9214
    Prev
    Next
    INDEX
    Explanations

    repetitive or rhythmic patterns, particularly with the use of certain phrases or words repeated multiple times

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or expressions of urgency and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illon
    -0.70
    imilar
    -0.67
    obook
    -0.65
    Organ
    -0.64
    arc
    -0.60
    é¾į
    -0.60
    Known
    -0.59
    Joshua
    -0.59
    ipel
    -0.59
    assian
    -0.59
    POSITIVE LOGITS
    !!!!
    1.10
    !!!!!
    1.07
    !!!
    1.05
    !!
    1.04
    !'
    1.04
    !.
    1.01
    !
    1.00
    oooo
    0.97
    !!"
    0.94
    !".
    0.94
    Activations Density 0.102%

    No Known Activations