© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 8489
    Prev
    Next
    INDEX
    Explanations

    names or references related to the Medellin Cartel

    oai_token-act-pair · gpt-3.5-turbo

    words related to media and the portrayal of drug-related subjects

    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
    ĸļ
    -0.83
    ©¶æ
    -0.76
    idan
    -0.68
    cknowled
    -0.62
    teenth
    -0.61
    Lay
    -0.59
     pancreat
    -0.59
    DATA
    -0.58
     intest
    -0.57
    ttle
    -0.57
    POSITIVE LOGITS
    ocre
    1.02
    coni
    0.93
    illions
    0.77
    apest
    0.69
    atters
    0.69
    anwhile
    0.68
    geist
    0.67
     CLSID
    0.66
    acus
    0.66
    opa
    0.65
    Activations Density 0.205%

    No Known Activations