INDEX

Explanations

elements related to various URLs or email addresses

oai_token-act-pair · gpt-3.5-turbo

locations or states with a focus on geographical or spatial references

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

accompan

-0.80

[*

-0.70

 Vaugh

-0.69

avorite

-0.68

 destro

-0.68

$$$$

-0.68

 helicop

-0.67

ãĥ¯ãĥ³

-0.66

 Jagu

-0.64

LCS

-0.63

POSITIVE LOGITS

 Profile

0.79

weed

0.61

hi

0.60

ser

0.59

fi

0.59

psy

0.58

ho

0.57

mosp

0.57

 Squirrel

0.56

hus

0.56

Activations Density 0.378%

elements related to various URLs or email addresses

locations or states with a focus on geographical or spatial references

No Comments

No Known Activations