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

VAL

-0.77

fleet

-0.71

SHIP

-0.71

ãĥ¯ãĥ³

-0.67

Queen

-0.65

 AUTHOR

-0.65

flow

-0.61

$$$$

-0.61

LIST

-0.61

CAP

-0.60

POSITIVE LOGITS

angan

0.75

achus

0.73

orescence

0.71

ogn

0.71

raft

0.70

yrim

0.70

ouls

0.68

owers

0.66

nces

0.66

athy

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.