INDEX

Explanations

terms related to medical conditions, treatments, and their outcomes

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>

-2.29

Descripció

-0.69

FileDescriptor

-0.67

private

-0.66

 AssemblyCompany

-0.66

namespace

-0.65

register

-0.65

base

-0.64

circ

-0.63

interface

-0.63

POSITIVE LOGITS

 increa

2.01

 affor

1.95

 impra

1.85

 stockholm

1.83

 sovere

1.82

 philanth

1.76

 strick

1.76

 volunte

1.75

 toledo

1.75

 hairc

1.75

Activations Density 0.365%

terms related to medical conditions, treatments, and their outcomes

No Comments

No Known Activations