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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 5669
    Prev
    Next
    INDEX
    Explanations

    phrases related to secret or hidden actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sneak" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.97
    minus
    -0.79
    nan
    -0.78
    rices
    -0.74
    onial
    -0.70
    acerb
    -0.69
    ĵĺ
    -0.68
    localhost
    -0.67
    Ĥİ
    -0.67
    ricular
    -0.67
    POSITIVE LOGITS
     sneak
    1.09
    ily
    1.05
     peek
    0.95
    door
    0.86
    away
    0.81
     glances
    0.78
    ipeg
    0.75
    iness
    0.74
    ously
    0.71
    iest
    0.70
    Activations Density 0.025%

    No Known Activations