INDEX

Explanations

the presence of words related to authority imposing actions or restrictions

oai_token-act-pair · gpt-3.5-turbo

words related to the act of imposing or enforcing regulations and sanctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

obby

-0.77

vironment

-0.76

razil

-0.74

sey

-0.71

 Emin

-0.70

wagen

-0.68

mpeg

-0.67

phia

-0.66

zo

-0.66

bucks

-0.65

POSITIVE LOGITS

 imposition

0.96

 imposed

0.94

 sanctions

0.86

 exerted

0.84

 harsher

0.83

 impose

0.83

 unnecess

0.82

 restrictions

0.82

 burdens

0.82

 stricter

0.81

Activations Density 0.027%

the presence of words related to authority imposing actions or restrictions

words related to the act of imposing or enforcing regulations and sanctions

No Comments

No Known Activations