INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

bold

-0.88

ï¸

-0.77

oak

-0.76

wagen

-0.72

oufl

-0.67

 Gloss

-0.67

 fixme

-0.67

 Roses

-0.66

^^^^

-0.66

Wee

-0.66

POSITIVE LOGITS

 worshipped

0.73

developed

0.72

 starved

0.70

hered

0.68

 awakened

0.67

apsed

0.67

 communal

0.66

 fused

0.66

 hunger

0.64

Saharan

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.