INDEX

Explanations

military ranks and related terms

oai_token-act-pair · gpt-3.5-turbo

references to music charts and major entities related to popular culture

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rily

-0.66

 poles

-0.65

ĸļ

-0.65

inea

-0.64

erella

-0.63

 Wonderland

-0.63

 darn

-0.61

wagen

-0.61

 Cosmos

-0.61

called

-0.61

POSITIVE LOGITS

clerosis

0.88

(>

0.80

ashtra

0.72

atform

0.70

andowski

0.66

vation

0.66

lycer

0.65

incial

0.64

jun

0.64

cohol

0.64

Activations Density 0.342%

military ranks and related terms

references to music charts and major entities related to popular culture

No Comments

No Known Activations