INDEX

Explanations

phrases related to 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.76

ⓧ

-1.06

<?

-0.93

/***

-0.92

/**

-0.86

-0.81

/*

-0.80

 modernize

-0.76

<?

-0.75

 harmonize

-0.73

POSITIVE LOGITS

 unlaw

1.07

 riva

0.94

 Keny

0.94

 pleins

0.94

 quoique

0.91

 seksi

0.91

 véhic

0.90

 unwarran

0.90

 Muhamma

0.90

 marea

0.89

Activations Density 0.175%

phrases related to people

No Comments

No Known Activations