INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 fart

-0.64

uity

-0.64

Äĩ

-0.64

generated

-0.64

ki

-0.62

nesday

-0.62

roman

-0.62

 Malone

-0.61

Cola

-0.61

 Franco

-0.60

POSITIVE LOGITS

lux

0.65

pent

0.65

versible

0.64

hyp

0.63

crew

0.63

LX

0.62

LV

0.62

 vessel

0.62

 convict

0.60

pine

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.