INDEX

Explanations

passive voice statements

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was" and related verb forms indicating past actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 adjustment

-0.66

 correction

-0.66

inner

-0.66

 evolves

-0.65

 goodbye

-0.63

 entails

-0.62

 Needs

-0.61

 sexes

-0.61

 stripe

-0.60

 emphasis

-0.60

POSITIVE LOGITS

 assassinated

0.87

icz

0.82

uala

0.82

senal

0.81

 reportedly

0.78

 congratulated

0.77

ŃĶ

0.77

 likewise

0.76

 accused

0.76

 sentenced

0.75

Activations Density 0.374%

passive voice statements

instances of the verb "was" and related verb forms indicating past actions

No Comments

No Known Activations