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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Issue

-0.71

ippery

-0.65

UA

-0.64

arton

-0.61

vous

-0.61

Episode

-0.60

Grade

-0.60

Story

-0.59

ploma

-0.59

close

-0.59

POSITIVE LOGITS

ilater

0.75

0.74

icators

0.72

icative

0.72

ction

0.71

til

0.68

ãĤ¡

0.67

][

0.66

naires

0.65

bys

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.