INDEX

Explanations

words related to tools, tasks, or actions related to using tools

oai_token-act-pair · gpt-3.5-turbo

words or phrases related to actions and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 saturated

-0.64

 curv

-0.63

 unaff

-0.63

 tremend

-0.61

 blister

-0.61

liv

-0.61

 unfor

-0.61

 corrid

-0.61

 SERV

-0.60

 borderline

-0.60

POSITIVE LOGITS

tenance

1.46

theless

1.22

terday

1.09

lihood

1.08

cipline

0.97

rentice

0.94

ythm

0.93

racuse

0.92

DragonMagazine

0.92

ruction

0.91

Activations Density 0.179%

words related to tools, tasks, or actions related to using tools

words or phrases related to actions and decisions

No Comments

No Known Activations