INDEX

Explanations

phrases related to reciprocal exchanges or negotiations

oai_token-act-pair · gpt-3.5-turbo

phrases involving exchanges or transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

inventoryQuantity

-0.97

rovers

-0.90

aval

-0.90

ocaly

-0.76

roach

-0.75

uyomi

-0.75

meta

-0.75

 collisions

-0.74

iasco

-0.73

regor

-0.70

POSITIVE LOGITS

 indemn

1.27

 agreeing

1.20

 guarantees

1.16

 assurances

1.11

 relinqu

1.10

 repayment

1.09

 payment

1.07

 concessions

1.07

 promised

1.04

 promise

1.03

Activations Density 0.368%

phrases related to reciprocal exchanges or negotiations

phrases involving exchanges or transactions

No Comments

No Known Activations