INDEX

Explanations

mentions of political figures and their affiliations

oai_token-act-pair · gpt-3.5-turbo

references to individuals identified by their titles or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

bugs

-0.79

Episode

-0.77

ADVERTISEMENT

-0.73

andom

-0.68

lift

-0.67

advertisement

-0.67

GROUP

-0.67

][/

-0.66

Characters

-0.65

pool

-0.65

POSITIVE LOGITS

 longtime

1.29

 staunch

1.24

 lifelong

1.19

 former

1.16

 devout

1.12

 native

1.11

 descendant

1.08

 fixture

1.07

 proponent

1.07

 perennial

1.06

Activations Density 0.126%

mentions of political figures and their affiliations

references to individuals identified by their titles or roles

No Comments

No Known Activations