© 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. 7-RES-JB
    11. 8611
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of truth

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "truth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uled
    -0.77
    joining
    -0.69
    wana
    -0.69
    rotein
    -0.65
    ATA
    -0.65
    avy
    -0.65
     Rivals
    -0.64
    capacity
    -0.63
    ato
    -0.62
    senal
    -0.62
    POSITIVE LOGITS
    fulness
    1.31
    fully
    1.16
    iness
    0.88
    telling
    0.86
    psons
    0.84
    ulent
    0.82
    truth
    0.81
    ful
    0.80
     seeker
    0.79
    faced
    0.78
    Activations Density 0.022%

    No Known Activations