INDEX

Explanations

proper nouns, specifically names of people

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>

-2.95

/**

-0.90

ⓧ

-0.85

<?

-0.84

/*

-0.78

/***

-0.69

<?

-0.69

 springfox

-0.66

/*++

-0.61

POSITIVE LOGITS

 Eric

1.22

Eric

1.22

 véhic

1.15

 ERIC

1.14

 silikon

1.11

 eric

1.10

 soulign

1.09

 maroc

1.07

 panik

1.05

 catég

1.02

Activations Density 0.072%

proper nouns, specifically names of people

No Comments

No Known Activations