INDEX

Explanations

specific instructions or requests related to a process or action

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 footing

-0.86

 instinct

-0.75

 overt

-0.74

ŃĶ

-0.73

 manif

-0.73

ibur

-0.73

 settled

-0.71

 conservatism

-0.70

 inference

-0.70

 inward

-0.68

POSITIVE LOGITS

 Alternatively

1.48

 Additionally

1.44

 Depending

1.40

 However

1.35

 Please

1.32

 Also

1.29

 Otherwise

1.27

 Therefore

1.23

 Likewise

1.21

 Furthermore

1.21

Activations Density 0.656%

specific instructions or requests related to a process or action

punctuation marks, specifically periods

No Comments

No Known Activations