INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

esa

-0.75

Wem

-0.70

 Epstein

-0.70

emer

-0.65

ube

-0.65

ugi

-0.65

pert

-0.65

je

-0.65

 Dayton

-0.65

yden

-0.62

POSITIVE LOGITS

 rendition

0.71

Proof

0.68

 unlaw

0.67

GH

0.66

ullah

0.65

Analysis

0.63

ROR

0.62

 guiActiveUnfocused

0.62

Closure

0.62

rafted

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.