INDEX

Explanations

mentions or references to sparks and ignition

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "spark."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ordan

-0.79

phia

-0.74

uphem

-0.70

guyen

-0.70

etheless

-0.70

terday

-0.66

 hygiene

-0.66

 parasites

-0.66

ibaba

-0.66

uthor

-0.66

POSITIVE LOGITS

plug

1.08

lers

0.93

le

0.93

lest

0.91

lar

0.89

LES

0.88

lights

0.85

led

0.84

ling

0.84

ris

0.84

Activations Density 0.014%

mentions or references to sparks and ignition

occurrences of the word "spark."

No Comments

No Known Activations