INDEX

Explanations

references to specific geographical locations or directions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.90

 Sanderson

-0.57

 mettent

-0.53

 Pyrr

-0.52

 Duncan

-0.52

 Tierney

-0.51

 Kerr

-0.50

hdr

-0.50

Ales

-0.50

Kir

-0.49

POSITIVE LOGITS

 ritard

0.94

 paff

0.94

vna

0.92

 makro

0.91

 marseille

0.90

ohr

0.90

 juft

0.89

 broder

0.89

mef

0.89

 ftre

0.88

Activations Density 0.806%

references to specific geographical locations or directions

No Comments

No Known Activations