INDEX

Explanations

passive actions or events in past or present tense

oai_token-act-pair · gpt-3.5-turbo

passive voice constructions related to actions or states of being

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dinand

-0.66

issance

-0.65

 fame

-0.65

Lind

-0.65

 fiasco

-0.64

amina

-0.62

 resear

-0.62

 bothers

-0.61

inence

-0.59

 saga

-0.59

POSITIVE LOGITS

ģ«

0.94

 abound

0.93

 exchanged

0.84

 underway

0.76

ļé

0.73

shed

0.71

Ń·

0.71

²¾

0.71

TBD

0.71

shown

0.70

Activations Density 0.293%

passive actions or events in past or present tense

passive voice constructions related to actions or states of being

No Comments

No Known Activations