INDEX

Explanations

references to locations associated with the tech industry

oai_token-act-pair · gpt-3.5-turbo

mentions of Silicon Valley

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

earance

-0.79

leness

-0.75

cause

-0.72

etheless

-0.71

alogue

-0.69

album

-0.66

ãĤ¯

-0.65

vor

-0.65

pain

-0.64

bodied

-0.64

POSITIVE LOGITS

 Networks

0.85

Gap

0.82

 Silicon

0.79

 CEOs

0.78

 billionaires

0.78

 firms

0.73

 entrepreneur

0.73

 giants

0.73

 Consulting

0.73

 Hust

0.72

Activations Density 0.027%

references to locations associated with the tech industry

mentions of Silicon Valley

No Comments

No Known Activations