INDEX

Explanations

proper nouns related to a specific individual or entity

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.56

 Normdatei

-0.65

FieldDescriptor

-0.61

print

-0.58

Referencie

-0.57

Mediabestanden

-0.57

cout

-0.57

FunctionFlags

-0.56

sent

-0.55

send

-0.54

POSITIVE LOGITS

Ke

1.40

 shenan

1.34

Ke

1.29

Kej

1.14

 alberto

1.12

 wattpad

1.11

 felipe

1.11

 pixar

1.09

 jurassic

1.06

 peppa

1.06

Activations Density 0.283%

proper nouns related to a specific individual or entity

No Comments

No Known Activations