© 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. 17146
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a failure to meet expectations or standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inadequacy or failure to meet expectations

    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
    antine
    -0.72
    uo
    -0.69
    Il
    -0.68
    RAW
    -0.67
    allic
    -0.66
    ILLE
    -0.65
    uala
    -0.64
     Disp
    -0.63
    GEN
    -0.63
    ITAL
    -0.63
    POSITIVE LOGITS
    sighted
    1.05
    falls
    1.01
    ening
    0.86
    casts
    0.81
    eners
    0.77
    leaf
    0.76
    lived
    0.74
     enough
    0.70
    ened
    0.70
    skirts
    0.70
    Activations Density 0.018%

    No Known Activations