INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "there."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Nanto

-0.62

 Higgins

-0.61

 attachments

-0.59

 Barney

-0.58

iencies

-0.58

eer

-0.58

 relevance

-0.57

 Tasman

-0.57

 Bast

-0.56

 Ventura

-0.56

POSITIVE LOGITS

abouts

1.86

upon

1.26

with

1.01

tics

1.00

tical

0.94

from

0.92

for

0.87

comings

0.87

fore

0.84

 guiActiveUn

0.81

Activations Density 0.089%

locations or places

occurrences of the word "there."

No Comments

No Known Activations