© 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. 6-RES-JB
    11. 2726
    Prev
    Next
    INDEX
    Explanations

    phrases related to updating or keeping informed

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing updates or monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.70
     Whats
    -0.68
     Primordial
    -0.66
     guiActiveUnfocused
    -0.63
     Tale
    -0.63
    CHA
    -0.62
     constituted
    -0.62
    hetti
    -0.61
     constit
    -0.60
    urally
    -0.60
    POSITIVE LOGITS
     gladly
    1.02
    Ĥ¬
    0.84
     laun
    0.82
    yss
    0.80
     ende
    0.78
     tomorrow
    0.68
     myself
    0.67
    rina
    0.66
     hereafter
    0.66
    mie
    0.66
    Activations Density 0.223%

    No Known Activations