INDEX

Explanations

mentions of bodies of water, such as seas, oceans, and waterfronts

oai_token-act-pair · gpt-3.5-turbo

terms related to marine life and the seafood industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

icle

-0.90

ivas

-0.89

haar

-0.83

win

-0.82

uate

-0.81

oday

-0.80

anu

-0.79

iva

-0.79

gart

-0.78

abel

-0.78

POSITIVE LOGITS

 seaf

1.08

 Seaf

1.08

 waterfront

1.00

 seafood

0.84

 Harbour

0.83

 shore

0.82

 seaw

0.80

 coastline

0.79

 Fisheries

0.79

 beach

0.79

Activations Density 0.018%

mentions of bodies of water, such as seas, oceans, and waterfronts

terms related to marine life and the seafood industry

No Comments

No Known Activations