INDEX

Explanations

time-related descriptions or mentions

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>

-3.45

ⓧ

-0.89

///**

-0.75

 inaugurate

-0.71

/***

-0.69

 mobilize

-0.65

 disbur

-0.64

 diversify

-0.63

 intensify

-0.62

 hasten

-0.61

POSITIVE LOGITS

 period

1.16

 Periods

1.12

 Period

1.12

Periods

1.06

period

1.05

periods

1.04

 pleins

1.04

Period

1.04

 maroc

1.02

 periods

1.02

Activations Density 0.084%

time-related descriptions or mentions

No Comments

No Known Activations