INDEX

Explanations

negative adjectives related to events or situations

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>

-3.11

Kontrola

-0.82

/***

-0.80

///**

-0.76

glBind

-0.73

//});

-0.69

//*/

-0.68

HasColumnType

-0.67

/*!

-0.66

<!--

-0.66

POSITIVE LOGITS

 napoli

1.38

capulco

1.35

 fatis

1.35

 dises

1.33

 ibiza

1.32

 toledo

1.32

 oleo

1.32

 cabrio

1.31

 bordeaux

1.30

 milano

1.29

Activations Density 0.605%

negative adjectives related to events or situations

No Comments

No Known Activations