INDEX

Explanations

terms related to technical information, potentially from bibliographic references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.20

 jsonString

-0.79

 flyknit

-0.78

 inconce

-0.77

 🤣🤣

-0.76

 nicolas

-0.72

 rafael

-0.70

 autunno

-0.70

 jeste

-0.69

POSITIVE LOGITS

 Info

0.96

Info

0.86

 info

0.86

info

0.80

 INFO

0.80

INFO

0.77

TypeInfo

0.71

getInfo

0.69

InfoWindow

0.62

NodeInfo

0.60

Activations Density 0.595%

terms related to technical information, potentially from bibliographic references

No Comments

No Known Activations