INDEX

Explanations

words related to a negative turn of events or actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing situations or conditions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cabinet

-0.68

 pickups

-0.66

ally

-0.62

 Passive

-0.61

 Galile

-0.60

 Boxing

-0.59

ions

-0.58

 queen

-0.58

 Franch

-0.58

 Saying

-0.58

POSITIVE LOGITS

 reminiscent

0.79

ģĸ

0.77

é¾įå¥ĳå£«

0.77

 culminated

0.74

 antit

0.74

nown

0.73

 underpin

0.73

 culmin

0.73

sole

0.72

 sorely

0.70

Activations Density 0.276%

words related to a negative turn of events or actions

phrases indicating ongoing situations or conditions

No Comments

No Known Activations