INDEX

Explanations

words related to creating a spark or ignition

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spark" used 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

guyen

-0.80

thodox

-0.78

etheless

-0.74

culosis

-0.71

uclear

-0.70

sembly

-0.67

ibaba

-0.67

 survive

-0.66

paio

-0.66

phia

-0.66

POSITIVE LOGITS

plug

1.04

 spark

1.02

notes

0.87

Fun

0.82

le

0.81

dust

0.81

 sparking

0.79

lights

0.78

lings

0.78

LES

0.78

Activations Density 0.007%

words related to creating a spark or ignition

instances of the word "spark" used in various contexts

No Comments

No Known Activations