INDEX

Explanations

words related to potential situations or hypothetical conditions

oai_token-act-pair · gpt-3.5-turbo

references to hypothetical situations or scenarios

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

ighters

-0.80

ances

-0.79

vation

-0.77

anguages

-0.77

enfranch

-0.77

ove

-0.76

nuts

-0.76

itsch

-0.75

tein

-0.75

oves

-0.75

POSITIVE LOGITS

 scenario

1.04

 scenarios

0.97

 involving

0.87

 unfold

0.79

 unfolding

0.78

0.74

 whereby

0.70

 wherein

0.70

 unfolds

0.69

ttes

0.67

Activations Density 0.024%

words related to potential situations or hypothetical conditions

references to hypothetical situations or scenarios

No Comments

No Known Activations