INDEX

Explanations

formats consistent with TV show or movie titles

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

inator

-0.70

¿½

-0.69

allel

-0.68

unia

-0.64

Ĥ¬

-0.61

 abundance

-0.61

Ń

-0.60

imon

-0.59

inators

-0.59

orf

-0.58

POSITIVE LOGITS

(*

0.68

tm

0.68

catentry

0.66

Deal

0.65

#$

0.61

Math

0.60

 sheet

0.60

berra

0.58

();

0.57

 olds

0.57

Activations Density 0.049%

formats consistent with TV show or movie titles

special characters or symbols in the text

No Comments

No Known Activations