INDEX

Explanations

words related to presentations and discussions

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

 santiago

-0.70

 utop

-0.69

 pican

-0.69

 coti

-0.67

 Rois

-0.66

 Julián

-0.65

 suspic

-0.65

 repug

-0.65

 ausp

-0.64

 notor

-0.63

POSITIVE LOGITS

 presentation

1.19

 presented

1.10

 presenting

1.10

 presents

1.09

presentation

1.09

 presenter

1.08

 Presentation

1.07

 presentations

1.07

presenter

1.01

 presenters

0.99

Activations Density 0.089%

words related to presentations and discussions

No Comments

No Known Activations