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

aph

-0.83

 extermin

-0.80

theless

-0.79

izen

-0.70

ohm

-0.68

 orally

-0.67

etically

-0.67

abi

-0.66

odox

-0.66

omorph

-0.66

POSITIVE LOGITS

 Plate

0.78

 Refresh

0.73

 Grounds

0.68

 Serve

0.68

Lod

0.65

 Integrity

0.65

 Thumbnails

0.65

 Scores

0.65

 Prov

0.65

Dir

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.