INDEX

Explanations

mentions of actions or potential states, especially in relation to personal experiences

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>

-3.46

 AssemblyCompany

-0.75

ⓧ

-0.74

<?

-0.69

/***

-0.68

EndProject

-0.66

addComponent

-0.66

/*!

-0.64

HideFlags

-0.63

GTCX

-0.63

POSITIVE LOGITS

 affor

1.35

 chrysler

1.22

 milf

1.21

 maneu

1.21

 pollut

1.21

 lidl

1.19

 impra

1.15

 practition

1.13

 accla

1.11

 lamborghini

1.08

Activations Density 0.173%

mentions of actions or potential states, especially in relation to personal experiences

No Comments

No Known Activations