INDEX

Explanations

places or spaces being occupied or filled

oai_token-act-pair · gpt-3.5-turbo

terms related to occupying or being occupied 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

raft

-0.78

ect

-0.75

uber

-0.74

peer

-0.74

ortality

-0.71

Detect

-0.70

Roll

-0.70

corruption

-0.70

Fly

-0.67

brother

-0.66

POSITIVE LOGITS

 occupied

0.93

 territories

0.89

ments

0.83

 Territories

0.83

 occupying

0.83

iture

0.82

 Eighth

0.80

 Seventh

0.80

itures

0.76

 occupy

0.73

Activations Density 0.026%

places or spaces being occupied or filled

terms related to occupying or being occupied in various contexts

No Comments

No Known Activations