INDEX

Explanations

mentions of the word "Hunt" or derivatives like "hunted" or "hunting"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hun" 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 @ 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

•Sports-related features

No Comments

Negative Logits

IDA

-0.70

ruption

-0.66

ktop

-0.65

Hof

-0.65

 protected

-0.64

 Literary

-0.63

ãĤ´ãĥ³

-0.63

 Byrne

-0.62

 authorised

-0.61

AGE

-0.61

POSITIVE LOGITS

kered

1.15

cheon

1.01

nam

0.98

zees

0.98

ters

0.98

ting

0.93

itive

0.92

ãĤ§

0.91

tered

0.89

ger

0.89

Activations Density 0.032%

mentions of the word "Hunt" or derivatives like "hunted" or "hunting"

instances of the word "hun" in various contexts

No Comments

No Known Activations