© 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. 3-RES-JB
    11. 10795
    Prev
    Next
    INDEX
    Explanations

    instances of the word "problems" along with the contexts in which they appear

    oai_token-act-pair · gpt-3.5-turbo

    mentions of problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.85
    rib
    -0.83
    alty
    -0.80
    rica
    -0.77
    omical
    -0.73
    umber
    -0.72
    glass
    -0.69
    orks
    -0.69
    uclear
    -0.68
    bern
    -0.68
    POSITIVE LOGITS
     plag
    1.06
    hooting
    1.00
     problems
    0.91
     stemming
    0.86
    afety
    0.85
    hift
    0.81
     confronting
    0.81
     facing
    0.79
    etting
    0.79
     affecting
    0.76
    Activations Density 0.033%

    No Known Activations