INDEX

Explanations

terms related to abstract or tangible frameworks

oai_token-act-pair · gpt-3.5-turbo

references to conceptual frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

cial

-0.74

hib

-0.71

igi

-0.70

dream

-0.68

interest

-0.67

hiro

-0.65

 Griffith

-0.64

prom

-0.64

hemat

-0.63

hi

-0.63

POSITIVE LOGITS

 framework

1.17

 frameworks

0.95

framework

0.89

 Framework

0.85

eworks

0.73

 guidelines

0.73

strap

0.68

 builder

0.67

nsic

0.65

folio

0.65

Activations Density 0.014%

terms related to abstract or tangible frameworks

references to conceptual frameworks

No Comments

No Known Activations