INDEX

Explanations

mentions of specific locations or cities

oai_token-act-pair · gpt-3.5-turbo

names and terms associated with geographical locations and possibly cultural references

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

lander

-0.70

ra

-0.66

SAF

-0.66

ers

-0.64

 Crom

-0.62

 respons

-0.61

TG

-0.61

sch

-0.60

meric

-0.59

 Schw

-0.58

POSITIVE LOGITS

otle

0.93

ounters

0.70

okÃ©

0.70

Saharan

0.68

Ã±o

0.68

mson

0.68

okemon

0.65

Ļ½

0.65

«

0.63

agues

0.62

Activations Density 0.111%

mentions of specific locations or cities

names and terms associated with geographical locations and possibly cultural references

No Comments

No Known Activations