INDEX

Explanations

writing related to governmental processes, legalities, and political strategies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 emphat

-2.01

 suspic

-2.00

 maneu

-1.98

 excru

-1.95

 disagre

-1.94

 inconce

-1.90

 inev

-1.90

 reluct

-1.89

 viciss

-1.84

 accla

-1.84

POSITIVE LOGITS

 Otherwise

0.96

<eos>

0.85

↵↵

0.84

If

0.84

We

0.84

 This

0.81

 There

0.80

 That

0.80

 Should

0.80

And

0.79

Activations Density 0.387%

writing related to governmental processes, legalities, and political strategies

No Comments

No Known Activations