INDEX

Explanations

phrases related to providing guidance or instructions

oai_token-act-pair · gpt-3.5-turbo

textual references to guides or instructional content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ntil

-0.66

ammy

-0.65

 spect

-0.64

asted

-0.62

 forfeit

-0.62

 concess

-0.61

 ILCS

-0.60

 Mellon

-0.60

Osw

-0.59

Rated

-0.59

POSITIVE LOGITS

book

1.37

books

1.34

posts

1.11

guide

0.98

BOOK

0.94

kit

0.90

voy

0.89

 guide

0.85

 guides

0.84

tips

0.80

Activations Density 0.038%

phrases related to providing guidance or instructions

textual references to guides or instructional content

No Comments

No Known Activations