© 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. 11-RES-JB
    11. 17216
    Prev
    Next
    INDEX
    Explanations

    words related to pre-existing conditions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "x"

    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
    à¨
    -0.66
     NETWORK
    -0.63
    GROUND
    -0.63
     whole
    -0.62
     conditioning
    -0.59
    ANK
    -0.59
     deaf
    -0.58
     abiding
    -0.57
    à©
    -0.57
     Rough
    -0.57
    POSITIVE LOGITS
    aminer
    1.28
    peria
    1.28
    posure
    1.27
    odus
    1.26
    ample
    1.24
    cellence
    1.17
    avier
    1.15
    imity
    1.15
    pert
    1.13
    ercise
    1.12
    Activations Density 0.058%

    No Known Activations