© 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. 17165
    Prev
    Next
    INDEX
    Explanations

    various forms of stereotypes

    oai_token-act-pair · gpt-3.5-turbo

    references to stereotypes and myths

    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
    inth
    -0.80
    ateur
    -0.77
    ayan
    -0.75
    sterdam
    -0.74
    rique
    -0.72
    Sync
    -0.68
    undred
    -0.66
    ighth
    -0.66
    hner
    -0.66
    ucha
    -0.65
    POSITIVE LOGITS
     stereotyp
    0.98
     stereotype
    0.89
     stereotypes
    0.89
     notions
    0.81
    è¦ļéĨĴ
    0.81
     clich
    0.78
     msec
    0.73
     depictions
    0.73
     portray
    0.73
     Monstrous
    0.71
    Activations Density 0.047%

    No Known Activations