INDEX

Explanations

names of individuals

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>

-1.87

 gratify

-0.63

 forbade

-0.60

 mobilize

-0.59

 rehabilitate

-0.57

 mobilized

-0.56

 ویکی‌آمباردا

-0.55

 rejoiced

-0.54

 reinstate

-0.54

 prioritise

-0.54

POSITIVE LOGITS

Ken

1.62

KEN

1.57

Ken

1.54

ken

1.37

KEN

1.14

Kenneth

1.13

 Kenneth

1.13

 Keny

1.04

 kenzo

0.98

ken

0.97

Activations Density 0.306%

names of individuals

No Comments

No Known Activations