INDEX

Explanations

sequences representing mathematical functions and equations

oai_token-act-pair · gpt-3.5-turbo

characters and symbols commonly associated with ratings or scores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

netflix

-1.23

seys

-0.96

ngth

-0.87

bilt

-0.82

ropolitan

-0.81

CTV

-0.81

VILLE

-0.80

azine

-0.80

ersive

-0.79

POSITIVE LOGITS

xd

0.87

xf

0.81

 bounce

0.76

xe

0.76

xc

0.76

xb

0.71

 stalled

0.71

 clinch

0.71

xa

0.70

 decisive

0.69

Activations Density 0.047%

sequences representing mathematical functions and equations

characters and symbols commonly associated with ratings or scores

No Comments

No Known Activations