INDEX

Explanations

phrases related to giving excuses or forgiveness

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.29

-0.82

PrintStream

-0.71

DataInputStream

-0.63

StreamWriter

-0.61

},{

-0.58

DataOutputStream

-0.57

testng

-0.56

HttpPut

-0.56

fputs

-0.55

POSITIVE LOGITS

mef

1.28

 wien

1.24

aen

1.23

 maroc

1.23

 stockholm

1.22

 italia

1.21

kyo

1.21

 tramont

1.19

 milano

1.19

 palio

1.18

Activations Density 0.238%

phrases related to giving excuses or forgiveness

No Comments

No Known Activations