INDEX

Explanations

special characters and specific phrases used for formatting or identification, such as a unique symbol followed by a date

oai_token-act-pair · gpt-3.5-turbo

the presence of the character "âĢĭ" in various contexts

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

oresc

-0.88

orescence

-0.84

pless

-0.76

ffield

-0.72

creen

-0.71

 rooting

-0.70

otine

-0.67

glers

-0.65

arsity

-0.64

obbies

-0.64

POSITIVE LOGITS

1.02

0.96

Leaks

0.90

âĢ¢âĢ¢

0.85

Mich

0.79

0.77

Bloomberg

0.77

Kings

0.77

Harris

0.75

Toronto

0.73

Activations Density 0.006%

special characters and specific phrases used for formatting or identification, such as a unique symbol followed by a date

the presence of the character "âĢĭ" in various contexts

No Comments

No Known Activations