INDEX

Explanations

phrases indicating a judgment of evaluation or decision-making

oai_token-act-pair · gpt-3.5-turbo

the term "deemed" in contexts of judgment or evaluation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scrimmage

-0.72

 Hawks

-0.69

 Prospect

-0.66

 Semin

-0.65

 Caption

-0.63

 Practice

-0.63

 Trial

-0.63

 Panic

-0.62

 Lawn

-0.62

 Pack

-0.61

POSITIVE LOGITS

 deem

1.20

 deemed

1.04

phas

1.02

 deems

0.94

 fide

0.88

rences

0.87

geist

0.77

AFTA

0.74

miah

0.74

 disapprove

0.74

Activations Density 0.010%

phrases indicating a judgment of evaluation or decision-making

the term "deemed" in contexts of judgment or evaluation

No Comments

No Known Activations