INDEX

Explanations

phrases related to political elections and appointments among other surrounding activities

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>

-0.81

 unspeak

-0.78

 gaily

-0.76

Wtf

-0.70

 Whence

-0.67

 Monticello

-0.67

 Lmao

-0.66

 kani

-0.66

 unwarran

-0.65

 Placer

-0.64

POSITIVE LOGITS

Mur

1.06

Mur

0.94

MUR

0.86

MUR

0.84

 Murphy

0.79

mur

0.78

mur

0.78

0.69

Murphy

0.69

 majest

0.68

Activations Density 0.625%

phrases related to political elections and appointments among other surrounding activities

No Comments

No Known Activations