INDEX

Explanations

phrases related to detailed explanations or descriptions

oai_token-act-pair · gpt-3.5-turbo

references to detailed descriptions or explanations

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

aden

-0.73

Pyr

-0.70

onz

-0.67

qqa

-0.65

oj

-0.64

=-=-=-=-=-=-=-=-

-0.64

andom

-0.63

squ

-0.61

ople

-0.61

ingo

-0.61

POSITIVE LOGITS

 detail

1.15

 details

1.12

 detailed

1.01

 descriptions

0.98

 particulars

0.89

 explanations

0.87

detail

0.86

 outlines

0.83

 detailing

0.83

itatively

0.83

Activations Density 0.009%

phrases related to detailed explanations or descriptions

references to detailed descriptions or explanations

No Comments

No Known Activations