INDEX

Explanations

names of specific locations or events

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>

-1.06

República

-0.61

RTEE

-0.57

 Carla

-0.56

Cat

-0.55

Categoria

-0.54

Categorie

-0.53

Bước

-0.53

 autorytatywna

-0.53

 bruge

-0.53

POSITIVE LOGITS

 uncin

0.94

 frankfurt

0.89

Honest

0.89

 peppa

0.89

 isabel

0.88

 Honest

0.85

 maneu

0.84

Gre

0.82

 shenan

0.82

 riviera

0.81

Activations Density 0.629%

names of specific locations or events

No Comments

No Known Activations