INDEX

Explanations

the word "att" with varying levels of strength in the match

oai_token-act-pair · gpt-3.5-turbo

variations of the word "att."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 fentanyl

-0.67

lda

-0.66

 methyl

-0.65

 Galile

-0.64

SIL

-0.62

theless

-0.62

 intermedi

-0.60

 Uzbek

-0.59

 jaws

-0.59

 Britann

-0.58

POSITIVE LOGITS

anooga

1.47

ributes

1.29

ributed

1.17

itude

1.13

leground

1.11

orney

1.11

achment

1.08

idy

1.03

alion

1.03

ention

1.01

Activations Density 0.025%

the word "att" with varying levels of strength in the match

variations of the word "att."

No Comments

No Known Activations