INDEX

Explanations

short descriptions or summaries about online services or products

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>

-3.23

///**

-0.84

/***

-0.81

WriteAttribute

-0.74

//---

-0.71

RTDA

-0.69

RTLR

-0.68

ItemBackground

-0.68

PerformLayout

-0.67

JspWriter

-0.66

POSITIVE LOGITS

 maneu

2.07

 impra

1.94

 increa

1.94

 affor

1.86

 accla

1.85

 reluct

1.82

 disagre

1.82

 unspeak

1.77

 shenan

1.75

 indescri

1.71

Activations Density 1.650%

short descriptions or summaries about online services or products

No Comments

No Known Activations