INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

emi

-0.77

lege

-0.72

=-=-

-0.70

osexual

-0.65

thouse

-0.64

REDACTED

-0.63

anche

-0.62

TTL

-0.61

UTC

-0.61

/-

-0.61

POSITIVE LOGITS

atre

0.65

Bie

0.63

 Kiev

0.62

ike

0.58

esp

0.58

 stump

0.58

 mimic

0.58

oby

0.57

ordered

0.57

 appl

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.