INDEX

Explanations

phrases related to the location of an event or situation

oai_token-act-pair · gpt-3.5-turbo

references to locations or contexts within a nation or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

onna

-0.67

 Uriel

-0.63

gery

-0.61

agascar

-0.61

 viol

-0.60

 Taxes

-0.60

 ahead

-0.60

rex

-0.59

 torches

-0.58

vu

-0.58

POSITIVE LOGITS

 confines

1.68

 bounds

1.45

 boundaries

1.23

 limits

1.11

 parameters

1.08

 borders

1.04

 scope

1.00

 constraints

0.94

 realm

0.93

 radius

0.93

Activations Density 0.089%

phrases related to the location of an event or situation

references to locations or contexts within a nation or organization

No Comments

No Known Activations