© 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. 9-RES-JB
    11. 14373
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causes and effects of social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.71
     classy
    -0.69
    omics
    -0.66
    liv
    -0.65
    ection
    -0.64
    oat
    -0.62
    ops
    -0.62
    cision
    -0.61
    chan
    -0.60
    raph
    -0.58
    POSITIVE LOGITS
     impetus
    1.49
     motivation
    1.30
     justification
    1.24
     motivating
    1.23
     reason
    1.19
     motiv
    1.15
     pretext
    1.08
     basis
    1.04
     motive
    1.04
     rationale
    1.01
    Activations Density 0.553%

    No Known Activations