INDEX

Explanations

terms or phrases related to comparison or evaluation

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize comparisons or evaluations in terms of measurable criteria

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

resent

-0.77

oaded

-0.76

estern

-0.76

dinand

-0.72

****************

-0.70

 tatt

-0.69

avorite

-0.67

enegger

-0.65

oster

-0.64

oute

-0.64

POSITIVE LOGITS

pace

0.81

ames

0.81

pring

0.79

 terms

0.78

uman

0.77

cale

0.76

cape

0.76

terms

0.73

 parity

0.71

forth

0.70

Activations Density 0.025%

terms or phrases related to comparison or evaluation

phrases that emphasize comparisons or evaluations in terms of measurable criteria

No Comments

No Known Activations