INDEX

Explanations

keywords related to mounting and positioning objects

oai_token-act-pair · gpt-3.5-turbo

references to "mount" and its variations, particularly in the context of physical or structural components

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

Ô

-0.78

nesota

-0.76

Ð¼

-0.72

Ðº

-0.69

rx

-0.68

gen

-0.68

 Quincy

-0.67

ister

-0.67

 spoken

-0.66

gone

-0.65

POSITIVE LOGITS

aint

1.10

mounted

0.98

mount

0.96

aine

0.93

ain

0.88

 Everest

0.82

 mount

0.78

heny

0.78

raint

0.75

rons

0.74

Activations Density 0.042%

keywords related to mounting and positioning objects

references to "mount" and its variations, particularly in the context of physical or structural components

No Comments

No Known Activations