INDEX

Explanations

dates and events mentioned in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to specific films, events, or cultural products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Nope

-0.79

omething

-0.72

Unknown

-0.68

 crappy

-0.66

whatever

-0.61

Rather

-0.61

Instead

-0.60

existent

-0.60

something

-0.59

Sure

-0.58

POSITIVE LOGITS

 additionally

1.06

 also

1.03

 airs

1.00

 furthermore

0.83

 previously

0.80

 further

0.76

 Also

0.75

 totaled

0.74

also

0.73

 originally

0.72

Activations Density 0.586%

dates and events mentioned in various contexts

references to specific films, events, or cultural products

No Comments

No Known Activations