INDEX

Explanations

words related to organizations and institutions

oai_token-act-pair · gpt-3.5-turbo

references to organizations or institutions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gow

-0.77

vati

-0.75

alore

-0.73

matter

-0.72

eeper

-0.72

ibaba

-0.71

hra

-0.70

aceous

-0.68

dash

-0.65

anchez

-0.65

POSITIVE LOGITS

 Elements

0.81

 Nations

0.76

 sorts

0.76

 Conscious

0.69

 Voters

0.68

 Sciences

0.68

 Characters

0.67

 Letters

0.66

 Legends

0.64

 Things

0.64

Activations Density 0.107%

words related to organizations and institutions

references to organizations or institutions

No Comments

No Known Activations