INDEX

Explanations

terms related to political figures, government actions, and historical events

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

 kram

-1.10

 gend

-0.99

 lele

-0.99

Anm

-0.97

Nö

-0.96

 utop

-0.96

 teras

-0.90

duk

-0.88

mef

-0.88

 „,

-0.88

POSITIVE LOGITS

by

0.63

viewWillAppear

0.53

alnız

0.52

 poveznice

0.51

 oleh

0.51

epsfig

0.51

 Apesar

0.49

 logements

0.49

by

0.48

 dachshund

0.48

Activations Density 0.331%

terms related to political figures, government actions, and historical events

No Comments

No Known Activations