INDEX

Explanations

mentions of particular events or performances in various locations

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>

-1.52

ⓧ

-1.34

-1.21

/**

-1.06

<?

-1.02

/*

-0.91

}{||

-0.76

/***

-0.75

 EXPERIMENTS

-0.71

 hindurch

-0.67

POSITIVE LOGITS

 kram

1.29

 silikon

1.29

 Kategor

1.29

 plak

1.27

 alkoh

1.25

 kosme

1.25

 maksi

1.25

 seksi

1.20

 keramik

1.19

 panik

1.18

Activations Density 0.332%

mentions of particular events or performances in various locations

No Comments

No Known Activations