INDEX

Explanations

dates expressed in time and numbers with some emphasis on specific words

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 esternos

-0.53

 poveznice

-0.53

 bağlantılar

-0.51

-0.49

 Testamento

-0.47

Française

-0.46

 Италијани

-0.46

RectangleBorder

-0.45

 constate

-0.44

rativa

-0.44

POSITIVE LOGITS

 unwarran

1.20

 unspeak

1.15

 shewn

1.09

 unlaw

1.08

 onely

1.05

 apprehen

1.05

 Shakspeare

1.05

 disreg

1.05

 impractica

1.04

 disagre

1.03

Activations Density 0.878%

dates expressed in time and numbers with some emphasis on specific words

No Comments

No Known Activations