INDEX

Explanations

instances where something is being introduced or presented to others

oai_token-act-pair · gpt-3.5-turbo

phrases related to the act of introducing or presenting something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

fall

-0.72

ache

-0.72

unker

-0.71

psons

-0.70

falls

-0.70

sis

-0.67

iac

-0.65

 msec

-0.65

iami

-0.63

aylor

-0.62

POSITIVE LOGITS

 into

0.85

into

0.84

 INTO

0.79

 introduce

0.78

new

0.77

 introducing

0.73

 introduced

0.72

 anew

0.72

introdu

0.71

 legislation

0.71

Activations Density 0.043%

instances where something is being introduced or presented to others

phrases related to the act of introducing or presenting something

No Comments

No Known Activations