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

orah

-0.82

iling

-0.81

plet

-0.81

ppings

-0.78

ctors

-0.78

cribed

-0.76

iled

-0.75

ints

-0.74

ibel

-0.74

bs

-0.73

POSITIVE LOGITS

 papers

0.67

 autonom

0.65

senal

0.65

 assumption

0.64

Press

0.64

TTL

0.62

 ende

0.61

 behav

0.61

 arrang

0.61

 downwards

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.