INDEX

Explanations

acronyms related to organizations or regulatory bodies

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations, entities, or acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 gent

-0.70

 mixed

-0.69

hig

-0.66

 artificial

-0.66

 surn

-0.66

 consolidation

-0.65

 migr

-0.64

 contempor

-0.64

 blurred

-0.64

 corridors

-0.64

POSITIVE LOGITS

ADRA

0.98

orks

0.86

untu

0.85

Leaks

0.83

ÃŃn

0.82

Plex

0.82

enge

0.81

¬

0.81

isite

0.81

EGIN

0.79

Activations Density 0.252%

acronyms related to organizations or regulatory bodies

references to specific organizations, entities, or acronyms

No Comments

No Known Activations