INDEX

Explanations

references to ghosts

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.29

mm

-0.66

addPreferredGap

-0.62

HasColumnType

-0.62

glDelete

-0.62

public

-0.61

PreAuthorize

-0.60

Пра

-0.59

Đặc

-0.58

webElementXpaths

-0.58

POSITIVE LOGITS

 ghost

1.50

 Ghost

1.41

 ghosts

1.37

ghost

1.32

 Ghosts

1.30

Ghost

1.29

 thut

1.28

fte

1.20

ftu

1.19

 jati

1.18

Activations Density 0.262%

references to ghosts

No Comments

No Known Activations