INDEX

Explanations

phrases related to legal actions or decisions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the character 'Ŀ'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 unconscious

-0.84

userc

-0.79

 conception

-0.76

 obser

-0.73

 integ

-0.73

 cradle

-0.72

 canv

-0.70

 assemb

-0.70

Downloadha

-0.70

 subsequ

-0.69

POSITIVE LOGITS

Â¯

0.96

ï¸ı

0.90

VERTISEMENT

0.85

âĸ

0.82

âĢł

0.82

ï¸

0.82

tab

0.82

ef

0.76

Ĭ

0.76

Cub

0.76

Activations Density 0.247%

phrases related to legal actions or decisions

occurrences of the character 'Ŀ'

No Comments

No Known Activations