© 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. 10210
    Prev
    Next
    INDEX
    Explanations

    adjectives and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to contradictions and comparisons

    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
    ftime
    -0.71
    amus
    -0.70
    izabeth
    -0.69
     herself
    -0.64
     exodus
    -0.61
    onement
    -0.61
    legate
    -0.59
    usk
    -0.58
    lon
    -0.58
    ffen
    -0.58
    POSITIVE LOGITS
    they
    1.65
     They
    1.51
     they
    1.47
    They
    1.41
     THEY
    1.39
     ones
    1.14
    their
    1.11
    These
    1.10
     These
    1.08
    Their
    1.04
    Activations Density 0.716%

    No Known Activations