INDEX

Explanations

phrases indicating decisions or actions being taken/not taken by individuals or groups

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verb "have" and its various forms in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Spend

-0.77

 spends

-0.70

 cares

-0.64

 Discuss

-0.63

 recalls

-0.62

 loses

-0.62

[&

-0.61

 hates

-0.60

 detrim

-0.59

AAF

-0.58

POSITIVE LOGITS

 arisen

1.46

 been

1.40

been

1.33

 emerged

1.31

 occurred

1.24

 surfaced

1.22

 ensued

1.20

kell

1.13

 existed

1.09

 flowed

1.08

Activations Density 0.123%

phrases indicating decisions or actions being taken/not taken by individuals or groups

occurrences of the verb "have" and its various forms in different contexts

No Comments

No Known Activations