© 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. 10-RES-JB
    11. 9968
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and adherence to rules and principles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to problem-solving and critical thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.75
    quartered
    -0.67
    anamo
    -0.64
    itialized
    -0.63
    trak
    -0.61
     millenn
    -0.60
    ropolitan
    -0.59
     mourning
    -0.53
     mention
    -0.52
     ozone
    -0.52
    POSITIVE LOGITS
     regardless
    1.16
     rather
    1.08
     irrespective
    1.06
     instead
    1.02
     ASAP
    1.00
     whereas
    0.92
    .
    0.91
     whenever
    0.90
     wherever
    0.87
    ."
    0.85
    Activations Density 0.492%

    No Known Activations