Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23
    Prev
    Next
    INDEX
    Explanations

    names related to the individual "Mitnick."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mitnick" and related individuals in a context involving hacking and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the token "Mit"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.82
    ħĭ
    -0.81
    etheless
    -0.77
    scribe
    -0.75
    awei
    -0.74
    raltar
    -0.74
    romeda
    -0.72
     clipboard
    -0.72
     nudity
    -0.71
    ISM
    -0.70
    POSITIVE LOGITS
     Mit
    0.89
     Stam
    0.78
    engers
    0.76
    ulence
    0.74
     Spe
    0.74
    eway
    0.73
     Schw
    0.73
     Cla
    0.70
    icial
    0.69
    eport
    0.69
    Activations Density 0.025%

    No Known Activations