INDEX

Explanations

sentences related to decision-making and comparisons

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

 emphat

-2.10

 viciss

-2.03

 suspic

-1.98

 disagre

-1.96

 dises

-1.94

ftu

-1.94

 excru

-1.91

 reluct

-1.91

 inev

-1.90

fuf

-1.89

POSITIVE LOGITS

It

1.09

If

1.01

And

1.01

But

0.96

We

0.94

 They

0.94

You

0.94

 There

0.93

 Whether

0.91

 When

0.91

Activations Density 0.409%

sentences related to decision-making and comparisons

No Comments

No Known Activations