INDEX

Explanations

the word "Mount" with various contexts

oai_token-act-pair · gpt-3.5-turbo

references to various mountains

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

ļéĨĴ

-0.78

razil

-0.72

 language

-0.71

 briefs

-0.63

xx

-0.62

EEE

-0.61

IME

-0.60

OPLE

-0.59

âĸĪâĸĪ

-0.58

ctors

-0.58

POSITIVE LOGITS

aint

0.92

 Sinai

0.91

aine

0.91

ains

0.83

mount

0.83

castle

0.82

 Everest

0.81

ain

0.76

lake

0.76

roy

0.75

Activations Density 0.010%

the word "Mount" with various contexts

references to various mountains

No Comments

No Known Activations