© 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. 0-RES-JB
    6. 2756
    Prev
    Next
    INDEX
    Explanations

    mentions of "PA" (possibly referring to "Pennsylvania") with a strong preference for the specific term "PA 9"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the acronym "PA," indicating a focus on something related to Pennsylvania or organizations associated with it

    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
    eer
    -0.71
    avorite
    -0.70
     Lob
    -0.68
     Cyborg
    -0.66
    earch
    -0.66
     Simpson
    -0.65
    ô
    -0.65
     Eg
    -0.65
    worms
    -0.64
     totem
    -0.64
    POSITIVE LOGITS
     PA
    3.97
    PA
    2.17
     Pa
    1.52
     Pennsylvania
    1.36
     RA
    1.35
     VA
    1.30
     WA
    1.27
     RI
    1.25
     PL
    1.24
     BA
    1.23
    Activations Density 0.011%

    No Known Activations