INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oret

-0.71

igating

-0.71

igation

-0.71

ripp

-0.67

otional

-0.66

ahan

-0.66

ifting

-0.65

ring

-0.64

 Gadget

-0.64

ories

-0.63

POSITIVE LOGITS

cake

0.70

 Solitaire

0.70

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

0.69

 parchment

0.69

nep

0.68

ascript

0.68

Si

0.67

UTF

0.67

uci

0.66

ĪĴ

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.