INDEX

Explanations

words related to quotes or emphasizing a point with quotation marks

oai_token-act-pair · gpt-3.5-turbo

quoted phrases or direct speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 rall

-0.85

 Nieto

-0.76

Vog

-0.72

 matter

-0.70

 outfielder

-0.70

 Catal

-0.70

 accomp

-0.69

 Matters

-0.68

Hoy

-0.68

icz

-0.67

POSITIVE LOGITS

safe

1.24

normal

1.23

false

1.20

sufficient

1.18

catch

1.16

pure

1.16

mere

1.16

official

1.15

susp

1.14

liberal

1.13

Activations Density 0.128%

words related to quotes or emphasizing a point with quotation marks

quoted phrases or direct speech

No Comments

No Known Activations