INDEX

Explanations

phrases related to specific events or locations

oai_token-act-pair · gpt-3.5-turbo

the indefinite articles "a" and "an" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ã©r

-0.72

ontent

-0.71

brate

-0.70

 talents

-0.69

=""

-0.66

caster

-0.66

flows

-0.66

coins

-0.66

lly

-0.65

items

-0.65

POSITIVE LOGITS

 glance

0.91

 concess

0.85

 moment

0.85

 pivotal

0.80

 behest

0.80

 disadvantage

0.79

 outset

0.78

 university

0.78

 conference

0.78

 handful

0.78

Activations Density 0.122%

phrases related to specific events or locations

the indefinite articles "a" and "an" in the text

No Comments

No Known Activations