INDEX

Explanations

mentions of a specific location or entity - Andhra Pradesh

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Andhra Pradesh."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.87

 Spiegel

-0.71

 coping

-0.69

glers

-0.64

ĸļ

-0.62

 Klaus

-0.60

 Schwarz

-0.58

âĸĪâĸĪâĸĪâĸĪ

-0.58

 Endless

-0.57

Esp

-0.56

POSITIVE LOGITS

 Pradesh

1.35

otide

0.90

nect

0.82

osate

0.76

istic

0.73

ward

0.73

inders

0.72

gage

0.70

azard

0.70

ennes

0.68

Activations Density 0.022%

mentions of a specific location or entity - Andhra Pradesh

occurrences of the term "Andhra Pradesh."

No Comments

No Known Activations