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

staking

-0.92

 corpus

-0.72

etric

-0.69

sent

-0.69

rive

-0.67

istries

-0.67

Gi

-0.65

aan

-0.64

oÄŁ

-0.63

 seizure

-0.62

POSITIVE LOGITS

 -------

0.76

 ----

0.71

-)

0.66

................................

0.64

 ********************************

0.64

 Mods

0.63

 NAME

0.62

 backwards

0.62

MEN

0.62

PLIED

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.