INDEX

Explanations

references to specific locations or institutions, particularly focusing on informative content

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>

-2.14

<?

-0.60

<?

-0.58

/***

-0.58

 springfox

-0.55

浜

-0.53

 дописавши

-0.52

//!

-0.52

Platt

-0.50

/****

-0.50

POSITIVE LOGITS

Rec

1.25

REC

1.10

Rec

1.08

rec

1.04

 jawa

0.97

capulco

0.95

 ecru

0.94

 bandung

0.92

rec

0.85

 pagkak

0.84

Activations Density 0.289%

references to specific locations or institutions, particularly focusing on informative content

No Comments

No Known Activations