INDEX

Explanations

keywords related to advice and instruction

oai_token-act-pair · gpt-3.5-turbo

phrases that express caution or advice against certain actions

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

 requisite

-0.72

 unparalleled

-0.71

 stabilized

-0.64

 exemplary

-0.64

 ample

-0.63

 resid

-0.62

albeit

-0.62

nell

-0.61

izable

-0.61

 occupancy

-0.60

POSITIVE LOGITS

 unless

1.16

 yourselves

1.09

unless

1.05

 yourself

1.01

 Yourself

0.98

 blindly

0.94

 EVER

0.94

 prematurely

0.91

 unnecessarily

0.90

 lest

0.89

Activations Density 0.315%

keywords related to advice and instruction

phrases that express caution or advice against certain actions

No Comments

No Known Activations