INDEX

Explanations

phrases related to providing explanations or defining concepts

oai_token-act-pair · gpt-3.5-turbo

the word "where" in various contexts, indicating locations or settings

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

Negative Logits

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.67

ÂłÂłÂł

-0.63

rieve

-0.63

 Dance

-0.61

rolet

-0.60

 Epidem

-0.60

 Rite

-0.58

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.58

 Doctrine

-0.58

ME

-0.58

POSITIVE LOGITS

upon

1.57

soever

1.27

abouts

1.05

fore

1.04

owler

0.74

ever

0.73

ipl

0.73

ver

0.72

anooga

0.72

players

0.71

Activations Density 0.067%

phrases related to providing explanations or defining concepts

the word "where" in various contexts, indicating locations or settings

No Known Activations