INDEX

Explanations

terms related to making judgments or evaluations

oai_token-act-pair · gpt-3.5-turbo

phrases related to judgment and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ortium

-0.83

iland

-0.77

idon

-0.76

uthor

-0.75

reon

-0.72

eva

-0.71

zzi

-0.70

ublic

-0.68

hler

-0.68

hound

-0.67

POSITIVE LOGITS

 incompetence

0.79

worthiness

0.76

 toughness

0.75

 karma

0.75

 competence

0.74

 resemblance

0.73

 ILCS

0.73

 resemb

0.73

how

0.70

 correctness

0.69

Activations Density 0.161%

terms related to making judgments or evaluations

phrases related to judgment and evaluation

No Comments

No Known Activations