© 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. 3-RES-JB
    11. 10640
    Prev
    Next
    INDEX
    Explanations

    symbols or symbolic references within text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to symbolic meaning and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.82
    IER
    -0.75
    ulhu
    -0.74
    ossier
    -0.71
    AIR
    -0.70
    Und
    -0.70
     Mercy
    -0.68
    VEL
    -0.68
    agher
    -0.67
    hhh
    -0.66
    POSITIVE LOGITS
     symbolic
    1.11
     gesture
    0.95
     gestures
    0.89
     representations
    0.88
     significance
    0.87
     meanings
    0.86
     eclipse
    0.86
     symbolism
    0.84
     marking
    0.82
     observ
    0.80
    Activations Density 0.010%

    No Known Activations