INDEX

Explanations

phrases including the substring "tra" which may often relate to words like "traffic", "traumatic", "trailers", and "transfer"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "trait" or its variations

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

Pwr

-0.77

amental

-0.73

manship

-0.65

 Seym

-0.62

 Mortal

-0.62

lihood

-0.62

OK

-0.61

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.61

lists

-0.59

MODE

-0.59

POSITIVE LOGITS

quel

1.00

pez

0.98

pped

0.93

umat

0.93

umatic

0.93

verse

0.92

itored

0.91

ffic

0.91

pping

0.90

ppings

0.89

Activations Density 0.016%

phrases including the substring "tra" which may often relate to words like "traffic", "traumatic", "trailers", and "transfer"

instances of the word "trait" or its variations

No Comments

No Known Activations