INDEX

Explanations

information related to a distinguished feature or characteristic, like product descriptions with notable attributes or event details with specific dates and 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>

-3.20

ⓧ

-0.76

var

-0.76

public

-0.74

forChild

-0.73

const

-0.73

 immer

-0.71

 realize

-0.71

private

-0.70

Descripció

-0.70

POSITIVE LOGITS

 maneu

2.18

 affor

2.17

 increa

2.10

 reluct

2.07

Juf

2.06

 stockholm

2.01

 milf

2.01

 shenan

1.94

 accla

1.93

 wien

1.92

Activations Density 0.069%

information related to a distinguished feature or characteristic, like product descriptions with notable attributes or event details with specific dates and locations

No Comments

No Known Activations