INDEX

Explanations

special formatting or code-related elements in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

spesies

-0.65

 GenerationType

-0.62

Rhestr

-0.59

dafx

-0.56

 actionPerformed

-0.55

ressee

-0.54

":

-0.53

—

-0.53

_'.$

-0.52

POSITIVE LOGITS

0.93

[toxicity=0]

0.84

<eos>

0.79

0.77

0.73

0.72

0.69

</tr>

0.69

0.66

Activations Density 0.082%

special formatting or code-related elements in the text

No Comments

No Known Activations