INDEX

Explanations

mentions of alternatives or variations to something

oai_token-act-pair · gpt-3.5-turbo

mentions of alternatives in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

older

-0.90

hips

-0.76

oho

-0.74

ursed

-0.73

ldom

-0.72

Chicken

-0.71

urat

-0.69

reditary

-0.68

uchi

-0.67

 Bees

-0.66

POSITIVE LOGITS

 viewpoints

1.00

 lifestyles

1.00

 explanations

0.91

 viewpoint

0.90

 modes

0.84

 methods

0.82

 method

0.82

 therapies

0.81

 perspectives

0.81

 alternative

0.80

Activations Density 0.030%

mentions of alternatives or variations to something

mentions of alternatives in various contexts

No Comments

No Known Activations