INDEX

Explanations

mentions of geographical locations

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

iculty

-0.69

 dreams

-0.69

 fantasies

-0.67

enhagen

-0.66

ongevity

-0.66

ipeg

-0.65

itals

-0.64

 opin

-0.62

ategory

-0.61

icultural

-0.61

POSITIVE LOGITS

 supra

0.88

 Kinnikuman

0.88

LLC

0.86

Inc

0.84

tein

0.79

Ltd

0.76

LLP

0.75

Zen

0.75

 whence

0.75

 Berks

0.74

Activations Density 0.412%

mentions of geographical locations

punctuation marks, particularly commas

No Comments

No Known Activations