© 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. 3593
    Prev
    Next
    INDEX
    Explanations

    the word "Sun" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    the word "Sun" in various contexts

    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
    ussen
    -0.67
     captcha
    -0.62
     improv
    -0.62
     pneum
    -0.59
     houses
    -0.58
     elig
    -0.58
     Hodg
    -0.58
    assetsadobe
    -0.57
     posit
    -0.56
     probabilities
    -0.55
    POSITIVE LOGITS
    shine
    1.25
    beam
    1.15
    flower
    1.10
    light
    1.08
    burst
    1.03
    nis
    1.01
    sets
    0.98
    rise
    0.98
    belt
    0.97
    screen
    0.96
    Activations Density 0.022%

    No Known Activations