INDEX

Explanations

instances of the word "problem" occurring in the text

oai_token-act-pair · gpt-3.5-turbo

references to problems or issues 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

orks

-0.88

rib

-0.85

urses

-0.84

arnaev

-0.79

theless

-0.75

vez

-0.75

ript

-0.74

rica

-0.73

ron

-0.73

collar

-0.73

POSITIVE LOGITS

 plag

1.23

 solved

0.95

Problem

0.93

 solving

0.93

 confronting

0.82

 endemic

0.82

 facing

0.79

atical

0.79

 Chimera

0.79

atically

0.78

Activations Density 0.062%

instances of the word "problem" occurring in the text

references to problems or issues in various contexts

No Comments

No Known Activations