© 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. 2-RES-JB
    11. 941
    Prev
    Next
    INDEX
    Explanations

    the term "misleading."

    oai_token-act-pair · gpt-4-turbo

    phrases or words related to deception or incorrect information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "misleading" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dain
    -0.70
    mun
    -0.69
    gil
    -0.69
    itar
    -0.69
    Interstitial
    -0.67
    issue
    -0.67
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    %"
    -0.65
    aple
    -0.63
    foreseen
    -0.62
    POSITIVE LOGITS
     misled
    1.26
     mislead
    1.23
    ingly
    1.10
     misleading
    1.06
     deceive
    1.04
     deceived
    1.00
     misrepresent
    0.93
     confuse
    0.92
     dece
    0.91
     falsely
    0.79
    Activations Density 0.016%

    No Known Activations