INDEX

Explanations

phrases that include the word "there" indicating a statement or condition

oai_token-act-pair · gpt-3.5-turbo

the word "there" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.61

 Armored

-0.60

 Maze

-0.59

 Heights

-0.58

 wheelchair

-0.57

 externalToEVAOnly

-0.56

 eyeing

-0.56

 Ashton

-0.56

IPM

-0.54

 caffe

-0.52

POSITIVE LOGITS

upon

1.37

fore

1.31

abouts

1.27

after

1.23

FORE

1.09

 exists

1.08

for

1.04

 arises

1.03

with

1.03

from

0.94

Activations Density 0.112%

phrases that include the word "there" indicating a statement or condition

the word "there" in various contexts

No Comments

No Known Activations