INDEX

Explanations

words related to enjoyable experiences or activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fun" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ainer

-0.70

Availability

-0.67

obook

-0.67

ignt

-0.63

 Centauri

-0.62

idate

-0.62

acid

-0.62

 Lama

-0.62

Error

-0.61

å£«

-0.60

POSITIVE LOGITS

nels

1.71

nell

1.28

gal

1.19

nel

1.17

icular

0.99

ctory

0.94

pmwiki

0.92

ctors

0.91

ctor

0.90

eral

0.85

Activations Density 0.053%

words related to enjoyable experiences or activities

instances of the word "fun" in various contexts

No Comments

No Known Activations