INDEX

Explanations

proper nouns, particularly personal names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 myſelf

-0.93

 itſelf

-0.82

 Reſ

-0.80

 whoſe

-0.79

bibfield

-0.78

BibitemShut

-0.77

 pleaſure

-0.76

 ſeveral

-0.76

 houſe

-0.76

 purpoſe

-0.75

POSITIVE LOGITS

 Arthur

0.77

Arthur

0.74

 Ernest

0.68

Harold

0.66

 Henry

0.62

Ernest

0.61

 Harold

0.60

 Charles

0.60

Earl

0.60

 Earl

0.58

Activations Density 0.568%

proper nouns, particularly personal names

No Comments

No Known Activations