INDEX

Explanations

words related to statements or declarations made by public figures

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said" 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 @ 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

Tag

-0.75

 ILCS

-0.72

otion

-0.69

CLA

-0.68

=~=~

-0.68

Issue

-0.67

à¦

-0.67

thia

-0.66

email

-0.66

Lens

-0.63

POSITIVE LOGITS

 bluntly

0.95

 goodbye

0.87

 unequivocally

0.85

 sarcast

0.81

 emphatically

0.81

doms

0.79

 repeatedly

0.76

 passionately

0.74

 aloud

0.74

 afterward

0.70

Activations Density 0.252%

words related to statements or declarations made by public figures

instances of the word "said" in various contexts

No Comments

No Known Activations