© 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. 2724
    Prev
    Next
    INDEX
    Explanations

    phrases indicating judgment or evaluation of someone's characteristics or abilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases pertaining to negative self-perception or criticisms

    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
     Locations
    -0.80
     Trails
    -0.77
    NetMessage
    -0.76
    osate
    -0.76
    itures
    -0.75
    iners
    -0.73
     Destination
    -0.73
    ulia
    -0.71
    ulations
    -0.70
    glers
    -0.69
    POSITIVE LOGITS
     trustworthy
    1.22
     deserving
    1.19
     worthy
    1.16
     competent
    1.12
     capable
    1.09
     smarter
    1.09
     qualified
    1.08
     incapable
    1.05
     incompetent
    1.03
     talented
    1.02
    Activations Density 0.267%

    No Known Activations