INDEX

Explanations

requests to look at specific information or data for analysis or comparison

oai_token-act-pair · gpt-3.5-turbo

phrases that prompt the reader to examine or pay attention to something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ortunately

-0.69

iHUD

-0.66

EStreamFrame

-0.64

redict

-0.64

claimed

-0.61

Chart

-0.60

JUST

-0.60

 Methods

-0.59

wi

-0.57

hate

-0.57

POSITIVE LOGITS

ahead

0.88

finder

0.81

atio

0.76

enary

0.73

iger

0.71

emark

0.68

igible

0.67

ttes

0.67

ãĤ¶

0.67

udo

0.66

Activations Density 0.019%

requests to look at specific information or data for analysis or comparison

phrases that prompt the reader to examine or pay attention to something

No Comments

No Known Activations