© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20705
    Prev
    Next
    INDEX
    Explanations

    instances of the word "alter" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alter" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PU
    -0.77
    Phones
    -0.76
    DragonMagazine
    -0.74
    ILLE
    -0.72
    çĦ
    -0.70
    Vs
    -0.69
    STON
    -0.68
    Pred
    -0.68
    Money
    -0.68
    ILA
    -0.67
    POSITIVE LOGITS
     alters
    1.03
     alter
    0.92
     costumes
    0.83
    ments
    0.82
     wrench
    0.82
     altering
    0.82
     havoc
    0.79
     guiActiveUn
    0.78
     awaken
    0.76
     ego
    0.76
    Activations Density 0.009%

    No Known Activations