INDEX

Explanations

references to power capacity or production in megawatts (MW)

oai_token-act-pair · gpt-3.5-turbo

measurements of power output or capacity in megawatts (MW)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

++++++++++++++++

-0.68

 scratched

-0.66

Aki

-0.66

 skulls

-0.66

Rey

-0.65

 prone

-0.64

 thro

-0.64

bidden

-0.64

ãĥ«

-0.62

 communist

-0.61

POSITIVE LOGITS

MW

1.10

NT

0.96

ASS

0.94

NP

0.92

orst

0.90

DT

0.88

atts

0.88

emonic

0.88

ategory

0.86

amily

0.86

Activations Density 0.005%

references to power capacity or production in megawatts (MW)

measurements of power output or capacity in megawatts (MW)

No Comments

No Known Activations