INDEX

Explanations

adjectives describing experiences or situations

oai_token-act-pair · gpt-3.5-turbo

phrases that express certainty or likelihood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

chieve

-0.64

achev

-0.61

istries

-0.60

 Narc

-0.60

 Goldberg

-0.58

ariat

-0.58

tons

-0.57

olor

-0.56

++++++++++++++++

-0.56

 Alban

-0.55

POSITIVE LOGITS

eming

0.71

 accordingly

0.65

forth

0.64

emis

0.61

Contin

0.60

bender

0.60

hew

0.60

imately

0.59

Ear

0.59

LIA

0.59

Activations Density 0.625%

adjectives describing experiences or situations

phrases that express certainty or likelihood

No Comments

No Known Activations