INDEX

Explanations

keywords related to the term "Fire"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Fire" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ĸļ

-1.13

berra

-0.83

Ń·

-0.80

ļéĨĴ

-0.73

sembly

-0.72

 newsp

-0.71

esis

-0.71

 versa

-0.70

terday

-0.70

 fixme

-0.69

POSITIVE LOGITS

flies

1.14

fighter

1.00

storm

0.96

wolf

0.94

 Emblem

0.93

fighters

0.93

proof

0.88

bats

0.86

storms

0.85

fly

0.82

Activations Density 0.019%

keywords related to the term "Fire"

mentions of the term "Fire" in various contexts

No Comments

No Known Activations