INDEX

Explanations

highly specific data categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-0.77

 transfieras

-0.66

AxisAlignment

-0.65

Mar

-0.60

readystatechange

-0.59

cap

-0.58

########.

-0.57

complexContent

-0.57

Erfolge

-0.56

Initializable

-0.56

POSITIVE LOGITS

1.27

0.92

0.89

0.86

 leaſt

0.84

0.82

0.81

Activations Density 0.036%

highly specific data categories or classifications

No Comments

No Known Activations