INDEX

Explanations

words related to reasoning, justification, and explanation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the existence or state of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Inventory

-0.76

ÄŁ

-0.75

lez

-0.72

glers

-0.71

eks

-0.70

 congratulations

-0.69

lash

-0.65

 Highlights

-0.65

orage

-0.65

should

-0.64

POSITIVE LOGITS

 inherently

0.91

 inconvenient

0.89

 already

0.89

 cheaper

0.86

 intrinsically

0.86

 sensitive

0.85

 supposedly

0.84

 deemed

0.83

 inaccessible

0.81

 unpopular

0.80

Activations Density 0.316%

words related to reasoning, justification, and explanation

phrases indicating the existence or state of being

No Comments

No Known Activations