© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 3092
    Prev
    Next
    INDEX
    Explanations

    words related to deception or misrepresentation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to misrepresentation and distortion of information

    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
    rises
    -0.77
    force
    -0.72
    achine
    -0.70
    ¯¯¯¯
    -0.68
    ça
    -0.66
    spot
    -0.65
     hungry
    -0.65
    fi
    -0.64
    irez
    -0.63
    ====
    -0.63
    POSITIVE LOGITS
     misrepresent
    0.86
     inaccur
    0.84
     distortions
    0.82
     distort
    0.80
     distortion
    0.80
     inaccurate
    0.78
     falsely
    0.76
     distorted
    0.74
     omission
    0.73
     perceptions
    0.71
    Activations Density 0.062%

    No Known Activations