INDEX

Explanations

phrases related to a specific location, namely "home"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "home" and context related to it

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

"]=>

-0.72

ACTED

-0.71

umbs

-0.70

ĸļ

-0.69

ãģĨ

-0.68

immers

-0.68

veyard

-0.67

uality

-0.66

haps

-0.65

uel

-0.65

POSITIVE LOGITS

coming

0.97

 turf

0.86

wife

0.84

pun

0.81

opathy

0.80

comings

0.79

 depot

0.79

 courtyard

0.78

opathic

0.75

pages

0.74

Activations Density 0.029%

phrases related to a specific location, namely "home"

occurrences of the word "home" and context related to it

No Comments

No Known Activations