INDEX

Explanations

terms related to bold actions or statements

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "bold" describing actions or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Cheong

-0.88

ADS

-0.79

OTOS

-0.77

VA

-0.70

UTERS

-0.69

 COURT

-0.67

AW

-0.67

OTA

-0.66

Gun

-0.64

UT

-0.64

POSITIVE LOGITS

 bold

1.26

bold

1.25

 Ital

1.02

faced

0.97

 ital

0.93

face

0.91

 daring

0.84

itude

0.82

 Bold

0.79

éĹĺ

0.79

Activations Density 0.006%

terms related to bold actions or statements

the repeated use of the word "bold" describing actions or policies

No Comments

No Known Activations