© 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. 8-RES-JB
    11. 4106
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to deception or false representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atl
    -0.85
    abulary
    -0.68
     Sob
    -0.64
    sten
    -0.64
    sf
    -0.63
     Torn
    -0.63
    throp
    -0.63
    served
    -0.61
    cest
    -0.61
    tein
    -0.60
    POSITIVE LOGITS
     virtues
    0.92
    Downloadha
    0.89
    urance
    0.84
     innocence
    0.81
     curing
    0.81
     invincible
    0.77
     cures
    0.77
     neutrality
    0.76
     impartial
    0.76
     efficacy
    0.75
    Activations Density 0.301%

    No Known Activations