INDEX

Explanations

references to specific locations or entities followed by an action or state

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thood

-0.87

eed

-0.81

 because

-0.78

Ò

-0.76

 besides

-0.74

verage

-0.72

plete

-0.72

leeve

-0.71

tsy

-0.69

ago

-0.69

POSITIVE LOGITS

 slightest

1.03

 biggest

0.98

 entire

0.96

 majority

0.95

 simplest

0.95

 entirety

0.95

 temptation

0.94

 easiest

0.91

 greatest

0.91

 likelihood

0.90

Activations Density 0.279%

references to specific locations or entities followed by an action or state

occurrences of the word "the" in various contexts

No Comments

No Known Activations