INDEX

Explanations

phrases related to quotation marks and dialogue attribution

oai_token-act-pair · gpt-3.5-turbo

statements that convey a sense of uncertainty or reflection on past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cano

-0.77

 censor

-0.75

 whip

-0.75

arde

-0.73

 regenerate

-0.70

 endeav

-0.69

 realised

-0.69

 censored

-0.68

inous

-0.68

 maths

-0.67

POSITIVE LOGITS

Indeed

1.14

Contribut

1.11

Attempts

1.06

Newsletter

1.00

Researchers

0.99

Eventually

0.97

RELATED

0.97

Despite

0.96

Fortunately

0.94

Still

0.94

Activations Density 0.189%

phrases related to quotation marks and dialogue attribution

statements that convey a sense of uncertainty or reflection on past events

No Comments

No Known Activations