© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3070
    Prev
    Next
    INDEX
    Explanations

    phrases related to something or someone falling into a negative situation or outcome

    oai_token-act-pair · gpt-3.5-turbo
    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
     indu
    -0.76
    zai
    -0.67
    die
    -0.66
    okia
    -0.64
    ennis
    -0.62
    eka
    -0.61
    Bey
    -0.60
    yip
    -0.59
    cies
    -0.59
    killer
    -0.58
    POSITIVE LOGITS
     obscurity
    0.83
     adulthood
    0.83
     Valhalla
    0.80
    clusion
    0.76
     darkness
    0.75
     orbit
    0.74
     limbo
    0.73
     Disorder
    0.71
     Darkness
    0.69
     homelessness
    0.66
    Activations Density 0.070%

    No Known Activations