INDEX

Explanations

terms or phrases used to describe various concepts or situations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate definitions or descriptions of terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ¥µ

-0.79

vez

-0.70

Hart

-0.70

ettel

-0.69

ath

-0.66

worm

-0.66

owsky

-0.65

worms

-0.65

bj

-0.65

POSITIVE LOGITS

 plural

0.85

 pronunciation

0.79

 abbre

0.78

 initials

0.76

 pronounced

0.74

 noun

0.73

 shorthand

0.70

 expressions

0.65

earable

0.64

bidden

0.64

Activations Density 0.152%

terms or phrases used to describe various concepts or situations

phrases that indicate definitions or descriptions of terms

No Comments

No Known Activations