INDEX

Explanations

government-related terms and actions

oai_token-act-pair · gpt-3.5-turbo

modal verbs indicating future actions or obligations from the government

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usalem

-0.68

Brit

-0.67

 calib

-0.66

CTV

-0.66

 compat

-0.63

Atl

-0.62

oplan

-0.62

 caliber

-0.62

 Circle

-0.62

cester

-0.61

POSITIVE LOGITS

 appoint

0.99

 annex

0.90

 reimb

0.87

 unilaterally

0.84

 appointing

0.83

 announce

0.80

 issuing

0.79

 consulted

0.79

 reimburse

0.78

 nominate

0.78

Activations Density 0.357%

government-related terms and actions

modal verbs indicating future actions or obligations from the government

No Comments

No Known Activations