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

 UNCLASSIFIED

-0.74

OURCE

-0.64

 orthodoxy

-0.59

 Â¥

-0.59

 corps

-0.58

 Gaddafi

-0.57

ashi

-0.57

Nusra

-0.56

 waive

-0.56

say

-0.56

POSITIVE LOGITS

amaz

0.75

tti

0.71

ashington

0.69

bard

0.67

Hal

0.66

rets

0.66

gans

0.66

iman

0.66

ournals

0.66

lean

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.