© 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. 1-RES-JB
    11. 4895
    Prev
    Next
    INDEX
    Explanations

    phrases related to inappropriate actions or behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "inappropriate" and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.86
    iph
    -0.86
    stone
    -0.83
    rix
    -0.82
    glass
    -0.82
    abiding
    -0.79
    board
    -0.77
    neys
    -0.75
    eely
    -0.74
    ingen
    -0.74
    POSITIVE LOGITS
     inappropriate
    1.16
     improper
    0.96
     undermin
    0.85
     inappropriately
    0.84
     misuse
    0.81
     indecent
    0.80
     improperly
    0.79
     concess
    0.77
     interfered
    0.77
     mishand
    0.77
    Activations Density 0.012%

    No Known Activations