INDEX

Explanations

periods

oai_token-act-pair · gpt-3.5-turbo

sentences that indicate statements or declarations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utter

-0.82

 installments

-0.69

 royalty

-0.67

 transact

-0.66

 monopol

-0.65

 delusion

-0.65

 expense

-0.65

 closet

-0.64

 silly

-0.64

 victories

-0.64

POSITIVE LOGITS

 Additionally

0.94

 However

0.90

 Similarly

0.88

<|endoftext|>

0.88

 Furthermore

0.88

 Moreover

0.87

 Along

0.85

 Adding

0.85

 Instead

0.85

 Afterwards

0.85

Activations Density 0.289%

periods

sentences that indicate statements or declarations

No Comments

No Known Activations