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

ridor

-0.84

bia

-0.82

lando

-0.79

Elf

-0.78

cia

-0.77

Ã©e

-0.77

raise

-0.77

rontal

-0.76

racuse

-0.75

ocratic

-0.74

POSITIVE LOGITS

 surn

0.82

Sub

0.70

 subs

0.68

 Nights

0.65

verts

0.63

 snippets

0.63

 subscribers

0.62

 specials

0.61

 Spect

0.61

ADS

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.