INDEX

Explanations

descriptive terms related to fragrances

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>

-2.98

<",

-0.86

ⓧ

-0.85

/***

-0.81

Autoritní

-0.80

AutoScaleMode

-0.78

 Roskov

-0.77

 Walkover

-0.77

 ***!

-0.77

///**

-0.76

POSITIVE LOGITS

 affor

1.28

 impra

1.20

 scrat

1.18

 embodi

1.16

 soulign

1.14

 maneu

1.12

 bosch

1.11

 friable

1.10

 increa

1.10

 disreg

1.06

Activations Density 0.370%

descriptive terms related to fragrances

No Comments

No Known Activations