INDEX

Explanations

phrases containing the word "stop" with a high degree of relevance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "stop."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

yss

-0.67

aths

-0.67

 suscept

-0.67

Versions

-0.61

Sov

-0.61

 roomm

-0.59

 Lair

-0.59

ighth

-0.58

ophon

-0.58

actionDate

-0.57

POSITIVE LOGITS

gap

1.43

watch

1.22

lights

1.14

overs

1.06

over

0.99

light

0.97

oppers

0.89

motion

0.82

iem

0.82

points

0.77

Activations Density 0.029%

phrases containing the word "stop" with a high degree of relevance

occurrences of the word "stop."

No Comments

No Known Activations