© 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. 10-RES-JB
    11. 21373
    Prev
    Next
    INDEX
    Explanations

    words related to negative or alarming information

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to alarming or disturbing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.84
    uay
    -0.79
    hops
    -0.79
    uilding
    -0.78
    ategory
    -0.77
    umers
    -0.75
    iership
    -0.72
    ileged
    -0.72
    yip
    -0.72
    iven
    -0.72
    POSITIVE LOGITS
     coincidence
    1.20
     statistic
    1.18
     revelation
    1.10
     implication
    1.09
     resemblance
    1.09
     inconsistency
    1.09
     revelations
    1.08
     omission
    1.05
     similarity
    1.05
     tale
    1.02
    Activations Density 0.142%

    No Known Activations