INDEX

Explanations

words that end in 'ed'

oai_token-act-pair · gpt-3.5-turbo

occurrences of prefixes or root words that suggest a state or action

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

 kittens

-0.67

Reviewer

-0.65

 Whats

-0.63

OHN

-0.62

accompan

-0.62

Ü

-0.57

 operators

-0.56

 davidjl

-0.55

whatever

-0.55

eps

-0.55

POSITIVE LOGITS

ividual

1.01

urities

0.83

uable

0.76

asonic

0.74

inately

0.73

uments

0.73

itably

0.73

ible

0.73

iever

0.72

umerable

0.70

Activations Density 0.088%

words that end in 'ed'

occurrences of prefixes or root words that suggest a state or action

No Comments

No Known Activations