INDEX

Explanations

phrases related to specific card games or strategies

oai_token-act-pair · gpt-3.5-turbo

references to specific characters or elements in a game context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AMES

-0.78

 commer

-0.75

yright

-0.75

 fucked

-0.74

çĶ°

-0.73

 licens

-0.71

 christ

-0.69

 lobb

-0.68

 physicists

-0.68

 supervised

-0.67

POSITIVE LOGITS

 Cloak

1.16

 Totem

1.15

Blade

1.11

 Primordial

1.11

 Golem

1.09

Spell

1.08

Orb

1.08

 Protector

1.06

 Blessing

1.06

 Haste

1.04

Activations Density 0.110%

phrases related to specific card games or strategies

references to specific characters or elements in a game context

No Comments

No Known Activations