INDEX

Explanations

phrases related to a process of certification, often involving reconsideration, or repetition

oai_token-act-pair · gpt-3.5-turbo

instances of the word "rec" in various forms related to recognition and reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MENTS

-0.78

loo

-0.77

furt

-0.72

nuts

-0.72

)=(

-0.71

NESS

-0.70

 Masters

-0.70

 Gemini

-0.69

MENT

-0.69

bags

-0.69

POSITIVE LOGITS

ourses

1.08

ievers

1.05

ursion

1.04

onduct

1.03

uters

1.03

occ

1.03

urrence

1.02

ategor

1.01

secut

1.01

oding

0.99

Activations Density 0.008%

phrases related to a process of certification, often involving reconsideration, or repetition

instances of the word "rec" in various forms related to recognition and reporting

No Comments

No Known Activations