INDEX

Explanations

adjectives with the prefix 'non-' or the stem 'nucle'

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'n' 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 @ 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

•·ΘΘΘΘ

No Comments

Negative Logits

 upside

-0.73

 asleep

-0.68

 frank

-0.65

 slack

-0.65

 contacting

-0.63

Vaj

-0.63

 inund

-0.59

 Agent

-0.59

 cand

-0.59

 lung

-0.59

POSITIVE LOGITS

aturally

1.45

onsense

1.45

autical

1.35

umbers

1.35

aughty

1.34

umerous

1.31

ihil

1.31

aked

1.30

umbing

1.28

orthern

1.28

Activations Density 0.043%

adjectives with the prefix 'non-' or the stem 'nucle'

instances of the letter 'n' in various contexts

No Comments

No Known Activations