INDEX

Explanations

the word "Dar" with varying degrees of strength

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Dar" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Gleaming

-0.73

 independents

-0.71

 habitable

-0.71

sburgh

-0.70

é¾įå¥ĳå£«

-0.69

 Skydragon

-0.68

ħĭ

-0.67

 Remastered

-0.67

 Dangerous

-0.64

*/(

-0.63

POSITIVE LOGITS

lington

1.42

rah

1.15

ien

1.14

fur

1.11

rington

1.08

agh

1.06

wyn

1.06

ienne

1.03

ques

1.02

izon

1.01

Activations Density 0.018%

the word "Dar" with varying degrees of strength

occurrences of the name "Dar" in various contexts

No Comments

No Known Activations