INDEX

Explanations

locations or entities with the word "lin" in them

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lin" in various contexts

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

awei

-0.92

 Seym

-0.84

rahim

-0.77

ansas

-0.77

ģĸ

-0.72

kward

-0.70

illed

-0.70

lished

-0.68

dyl

-0.66

ModLoader

-0.66

POSITIVE LOGITS

ergic

1.10

eman

0.93

ium

0.91

burg

0.90

 Rouge

0.87

phrine

0.85

strument

0.85

hurst

0.84

emen

0.82

fo

0.81

Activations Density 0.022%

locations or entities with the word "lin" in them

occurrences of the word "lin" in various contexts

No Comments

No Known Activations