© 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. 7-RES-JB
    11. 17170
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by a verb indicating action or opinion

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the collective pronoun "They."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CCC
    -0.78
     Eleven
    -0.77
    duc
    -0.64
    INGTON
    -0.64
    Govern
    -0.63
     Amen
    -0.62
    DAY
    -0.62
     Sirius
    -0.61
     Innocent
    -0.61
    âĺħâĺħ
    -0.60
    POSITIVE LOGITS
    're
    1.24
    zbollah
    1.12
    'll
    1.10
    selves
    1.07
    've
    1.05
    pherd
    0.99
    gemony
    0.96
    resy
    0.91
    'd
    0.90
    miah
    0.86
    Activations Density 0.164%

    No Known Activations