INDEX

Explanations

verbs associated with giving commands or making demands

oai_token-act-pair · gpt-3.5-turbo

references to commands, orders, and demands in authoritative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

verage

-0.82

allery

-0.79

rily

-0.72

edge

-0.71

iencies

-0.69

vae

-0.69

aples

-0.68

Studies

-0.68

issance

-0.67

NX

-0.67

POSITIVE LOGITS

 letter

0.90

 granting

0.86

 granted

0.84

 forb

0.83

 urging

0.83

 requesting

0.83

 prohibiting

0.82

 begging

0.82

 issued

0.82

 dated

0.81

Activations Density 0.196%

verbs associated with giving commands or making demands

references to commands, orders, and demands in authoritative contexts

No Comments

No Known Activations