INDEX

Explanations

abbreviations related to professional titles and organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific titles or designated names, particularly in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

clerosis

-0.69

schild

-0.64

IGHTS

-0.63

 unfocusedRange

-0.61

anmar

-0.60

inem

-0.59

 Admir

-0.59

UCT

-0.58

 Peaks

-0.57

enegger

-0.57

POSITIVE LOGITS

ongyang

0.90

ĵĺ

0.79

 Lovecraft

0.73

facebook

0.72

asus

0.71

twitter

0.69

illin

0.69

gran

0.68

bara

0.67

ciation

0.66

Activations Density 0.051%

abbreviations related to professional titles and organizations

references to specific titles or designated names, particularly in a structured format

No Comments

No Known Activations