INDEX

Explanations

phrases related to criticism or judgment

oai_token-act-pair · gpt-3.5-turbo

letters or letter combinations that denote some form of classification or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

enhagen

-0.90

å§«

-0.80

EStream

-0.79

 Shepherd

-0.75

LEY

-0.73

ħĭ

-0.73

 Puzzles

-0.72

İĭ

-0.72

 Lauder

-0.69

©¶æ¥µ

-0.69

POSITIVE LOGITS

arc

1.01

ounded

0.91

arr

0.88

cd

0.87

actory

0.86

anc

0.86

umbers

0.84

icked

0.84

arching

0.83

pc

0.82

Activations Density 0.126%

phrases related to criticism or judgment

letters or letter combinations that denote some form of classification or categorization

No Comments

No Known Activations