INDEX

Explanations

punctuation marks, specifically parentheses and colons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

BibitemShut

-0.89

$_"

-0.82

bibfield

-0.79

 pleaſure

-0.78

 déput

-0.76

 feroit

-0.75

 vérit

-0.74

protoimpl

-0.74

 mariée

-0.73

 kaarangay

-0.71

POSITIVE LOGITS

his

0.78

↵

0.75

>{@

0.65

0.64

him

0.62

0.59

↵↵

0.58

0.57

0.56

 himself

0.56

Activations Density 0.329%

punctuation marks, specifically parentheses and colons

No Comments

No Known Activations