INDEX

Explanations

adjectives describing physical characteristics or states

oai_token-act-pair · gpt-3.5-turbo

adjectives or adverbial forms that end with "ly."

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

uther

-0.90

ainer

-0.87

arte

-0.85

aver

-0.82

intern

-0.76

iffe

-0.75

acl

-0.73

regon

-0.72

avering

-0.72

href

-0.71

POSITIVE LOGITS

ly

0.88

 tones

0.86

 sounding

0.85

 affairs

0.84

 slopes

0.79

 affair

0.79

ulent

0.79

 terrain

0.76

 conco

0.76

 enterprises

0.75

Activations Density 0.086%

adjectives describing physical characteristics or states

adjectives or adverbial forms that end with "ly."

No Comments

No Known Activations