INDEX

Explanations

references to exploring, studying, or analyzing various topics and systems

oai_token-act-pair · gpt-3.5-turbo

phrases that explore the concept of "how" various processes or phenomena occur

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lehem

-0.80

hyde

-0.75

ãĥŃ

-0.74

ridor

-0.73

deen

-0.73

aredevil

-0.73

inth

-0.72

gur

-0.72

ktop

-0.70

ãĤ¹

-0.70

POSITIVE LOGITS

 differently

0.97

soever

0.91

 much

0.82

 disparate

0.79

 prevalent

0.79

 efficiently

0.78

 poorly

0.75

 easily

0.74

 seamlessly

0.74

 closely

0.74

Activations Density 0.094%

references to exploring, studying, or analyzing various topics and systems

phrases that explore the concept of "how" various processes or phenomena occur

No Comments

No Known Activations