INDEX

Explanations

keywords related to hypothetical situations or possibilities

oai_token-act-pair · gpt-3.5-turbo

mentions of different scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

-0.94

ixed

-0.85

ove

-0.82

hammad

-0.81

oves

-0.81

olulu

-0.79

obe

-0.78

alties

-0.77

azar

-0.77

umpy

-0.77

POSITIVE LOGITS

 scenario

1.06

 scenarios

1.02

eers

0.83

0.75

 involving

0.71

finder

0.71

 unfold

0.70

-+-+

0.69

Activations Density 0.009%

keywords related to hypothetical situations or possibilities

mentions of different scenarios

No Comments

No Known Activations