INDEX

Explanations

words related to intense, negative, or violent actions

oai_token-act-pair · gpt-3.5-turbo

words associated with harsh or unforgiving conditions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ullivan

-0.86

acular

-0.82

orem

-0.77

ators

-0.73

weeney

-0.73

ational

-0.72

orus

-0.71

istries

-0.71

trl

-0.70

ially

-0.69

POSITIVE LOGITS

CVE

0.79

 winters

0.76

 Thro

0.72

 unfor

0.71

cious

0.70

ãĥ©

0.69

 Clicker

0.67

 snowy

0.66

 honest

0.64

ãĤ¨

0.63

Activations Density 0.024%

words related to intense, negative, or violent actions

words associated with harsh or unforgiving conditions and experiences

No Comments

No Known Activations