© 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. 9-RES-JB
    11. 4948
    Prev
    Next
    INDEX
    Explanations

    phrases associated with false information or accusations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to false accusations or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hens
    -1.01
     guiActiveUnfocused
    -0.90
    hem
    -0.86
    xual
    -0.82
    ajo
    -0.73
    hetti
    -0.71
    oké
    -0.70
    alon
    -0.70
    rador
    -0.70
    icals
    -0.69
    POSITIVE LOGITS
     positives
    1.20
     dich
    0.95
     guiActiveUn
    0.95
     guiIcon
    0.94
     alarms
    0.92
     accusation
    0.91
     negatives
    0.89
     equival
    0.86
     accuser
    0.84
     modesty
    0.84
    Activations Density 0.038%

    No Known Activations