INDEX

Explanations

words related to mentioning or references in a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "mention" and its variations

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

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.94

Â¯Â¯

-0.73

Â¯Â¯Â¯Â¯

-0.69

zers

-0.69

sett

-0.68

uilt

-0.68

insula

-0.67

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.67

orneys

-0.67

heric

-0.67

POSITIVE LOGITS

 mentions

0.90

 mentioning

0.90

 Kislyak

0.76

lihood

0.75

enance

0.74

utra

0.70

 mention

0.67

 aloud

0.67

pages

0.65

 indexes

0.64

Activations Density 0.031%

words related to mentioning or references in a text

instances of the word "mention" and its variations

No Comments

No Known Activations