INDEX

Explanations

dates or time-related expressions

oai_token-act-pair · gpt-3.5-turbo

opening parentheses

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wagen

-0.76

 nuts

-0.75

 gems

-0.73

nesday

-0.72

 piping

-0.68

 overpowered

-0.65

 orchestr

-0.65

 intimid

-0.64

 obscurity

-0.63

 lull

-0.63

POSITIVE LOGITS

Reuters

1.15

UTERS

1.09

emphasis

1.00

CNN

0.99

Photo

0.94

credit

0.94

ICH

0.91

via

0.91

Phys

0.90

click

0.90

Activations Density 0.020%

dates or time-related expressions

opening parentheses

No Comments

No Known Activations