INDEX

Explanations

references to technical documentation and forums related to specific topics

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>

-0.87

DockStyle

-0.72

osoba

-0.63

complexType

-0.62

fortawesome

-0.61

Fer

-0.60

jspb

-0.59

 nakalista

-0.58

ositol

-0.58

UnknownFields

-0.57

POSITIVE LOGITS

 affor

1.38

 unspeak

1.34

 reluct

1.30

 stockholm

1.23

 impra

1.22

 apprehen

1.22

 🤣🤣

1.21

 inev

1.17

 shenan

1.16

 increa

1.16

Activations Density 0.695%

references to technical documentation and forums related to specific topics

No Comments

No Known Activations