© 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. 24096
    Prev
    Next
    INDEX
    Explanations

    phrases related to denial or rejection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "denied" in relation to allegations or claims

    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
    =-=-=-=-=-=-=-=-
    -0.91
    psc
    -0.84
    ROM
    -0.82
    sit
    -0.81
    cycl
    -0.77
    liam
    -0.77
    rouse
    -0.77
    ICAN
    -0.76
    Center
    -0.76
    OPER
    -0.75
    POSITIVE LOGITS
     denied
    1.16
     denies
    1.16
     deny
    1.05
     denying
    1.04
     denial
    0.89
     outright
    0.88
     rehe
    0.83
    ĸļ
    0.80
     dismissing
    0.77
     exclus
    0.75
    Activations Density 0.010%

    No Known Activations