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

hran

-0.72

Ø³

-0.70

è¯

-0.65

ÙĬ

-0.64

iety

-0.64

 behavi

-0.61

lc

-0.60

ilege

-0.59

 reviewer

-0.58

ascular

-0.58

POSITIVE LOGITS

 Tide

0.69

 Trace

0.65

 hump

0.63

SOS

0.63

MX

0.63

TTL

0.63

theless

0.61

payers

0.60

 Rubber

0.59

 immunity

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.