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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intent

-0.78

oves

-0.77

impact

-0.76

evidence

-0.73

AIDS

-0.72

assisted

-0.70

eyes

-0.70

Instruct

-0.67

ENT

-0.67

Ir

-0.66

POSITIVE LOGITS

 bunch

0.97

lot

0.88

 decent

0.88

usterity

0.85

 huge

0.82

 fantastic

0.81

 recurring

0.80

 handful

0.80

 simpler

0.79

 separate

0.79

Activations Density 0.000%

No Known Activations

This feature has no known activations.