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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atural

-0.73

nar

-0.70

essions

-0.67

itability

-0.65

iting

-0.63

":"/

-0.63

ESSION

-0.63

marine

-0.61

itus

-0.61

phia

-0.60

POSITIVE LOGITS

©¶æ

0.84

 destro

0.80

emb

0.77

ahon

0.73

 predec

0.73

GCC

0.73

Fib

0.72

undai

0.71

 assum

0.71

imedia

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.