INDEX

Explanations

terms related to some kind of primary aspect or focus

oai_token-act-pair · gpt-3.5-turbo

the term "primary" in various contexts related to significance or ranking

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

uge

-0.73

estern

-0.71

INESS

-0.70

glass

-0.68

EEK

-0.68

 Doodle

-0.67

 Feet

-0.66

phis

-0.66

sung

-0.66

LV

-0.64

POSITIVE LOGITS

 careg

0.91

tenance

0.88

 beneficiary

0.85

 antagonist

0.84

 responsibility

0.78

 culprit

0.78

iary

0.76

ities

0.74

 distingu

0.74

 pivot

0.74

Activations Density 0.018%

terms related to some kind of primary aspect or focus

the term "primary" in various contexts related to significance or ranking

No Comments

No Known Activations