INDEX

Explanations

instances of the word "checks".

oai_token-act-pair · gpt-3.5-turbo

references to verification or assessment processes, particularly those involving checks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

NAS

-0.80

âĹ¼

-0.76

LOD

-0.76

Anth

-0.73

SAY

-0.72

âĸ¬

-0.71

yss

-0.71

MER

-0.70

Brand

-0.70

Î¼

-0.69

POSITIVE LOGITS

 checks

1.30

checks

1.11

 Checks

1.05

 check

1.04

etts

0.94

umenthal

0.82

 checking

0.81

check

0.81

 checkpoints

0.81

ippi

0.79

Activations Density 0.010%

instances of the word "checks".

references to verification or assessment processes, particularly those involving checks

No Comments

No Known Activations