INDEX

Explanations

phrases related to decision-making or evaluations

oai_token-act-pair · gpt-3.5-turbo

instances of the conjunction "and."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AMY

-0.78

å¤©

-0.68

Way

-0.68

ardy

-0.67

Alias

-0.67

SourceFile

-0.65

!--

-0.65

ENCY

-0.64

İĭ

-0.63

NPR

-0.63

POSITIVE LOGITS

 determine

1.20

 decide

1.13

 conclude

1.12

 determining

1.10

 concluded

1.08

 ascertain

1.05

 evaluate

1.04

 assessing

1.02

 analyse

1.01

 evaluating

1.00

Activations Density 0.264%

phrases related to decision-making or evaluations

instances of the conjunction "and."

No Comments

No Known Activations