INDEX

Explanations

words related to interception or concept

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of intercepts 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 bourbon

-0.72

ISO

-0.63

 births

-0.61

 wives

-0.59

 Bourbon

-0.59

 Older

-0.59

 write

-0.59

 assignments

-0.59

 assignment

-0.58

 Frazier

-0.58

POSITIVE LOGITS

cept

4.72

ceptor

2.69

CEPT

1.81

ception

1.64

ceptive

1.53

ceptions

1.53

kept

1.44

ceived

1.41

ference

1.15

 scept

1.14

Activations Density 0.018%

words related to interception or concept

terms related to the concept of intercepts in various contexts

No Comments

No Known Activations