INDEX

Explanations

words related to specific names and locations, specifically those containing "kh"

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific name patterns or characters in names

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reaper

-0.80

swick

-0.78

phrine

-0.78

DIT

-0.75

IBLE

-0.72

sequ

-0.72

psons

-0.70

FOX

-0.69

 Collider

-0.67

LOAD

-0.67

POSITIVE LOGITS

azard

1.06

urst

1.05

ritis

0.99

alid

0.97

doms

0.96

aji

0.90

iggins

0.88

romy

0.88

owsky

0.86

rolet

0.85

Activations Density 0.022%

words related to specific names and locations, specifically those containing "kh"

occurrences of specific name patterns or characters in names

No Comments

No Known Activations