INDEX

Explanations

proper nouns and their associated details

oai_token-act-pair · gpt-3.5-turbo

references to a specific brand or type of product

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 fortun

-0.77

 mutually

-0.75

 deepening

-0.74

 fuse

-0.71

 prominently

-0.71

 scrut

-0.70

 WHERE

-0.70

 mathemat

-0.70

 funnel

-0.68

 levers

-0.67

POSITIVE LOGITS

ï¸ı

1.17

ski

1.08

iversary

0.95

ship

0.93

tsy

0.91

sky

0.90

mas

0.89

sin

0.88

tal

0.88

ember

0.87

Activations Density 0.282%

proper nouns and their associated details

references to a specific brand or type of product

No Comments

No Known Activations