INDEX

Explanations

positive descriptions involving temperature or behavior

oai_token-act-pair · gpt-3.5-turbo

the term "warm" and its variations or associations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

angler

-0.72

argon

-0.70

arge

-0.68

gur

-0.66

issors

-0.66

 UNITED

-0.65

iage

-0.64

Lay

-0.63

omething

-0.62

aurus

-0.62

POSITIVE LOGITS

achine

1.35

est

1.12

 fuzz

0.98

 fuzzy

0.93

 warm

0.92

ening

0.91

hearted

0.90

 blanket

0.89

water

0.81

warm

0.80

Activations Density 0.023%

positive descriptions involving temperature or behavior

the term "warm" and its variations or associations

No Comments

No Known Activations