© 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. 2-RES-JB
    11. 1029
    Prev
    Next
    INDEX
    Explanations

    words related to personal encounters or interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'experience.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hatt
    -0.79
    vous
    -0.76
    law
    -0.71
    ependent
    -0.70
    fam
    -0.68
     landsl
    -0.63
    yright
    -0.61
    sub
    -0.61
    yrics
    -0.60
    trap
    -0.60
    POSITIVE LOGITS
     Experience
    1.18
    Experience
    1.09
     experience
    1.04
     experiences
    1.01
    ttes
    0.87
    IENCE
    0.83
     experien
    0.82
    OWS
    0.80
    ually
    0.78
    iences
    0.78
    Activations Density 0.025%

    No Known Activations