INDEX

Explanations

mentions or instances of specific options

oai_token-act-pair · gpt-3.5-turbo

references to various choices or alternatives

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

mind

-0.78

hemat

-0.77

soever

-0.72

olds

-0.69

rollers

-0.69

ilipp

-0.67

tub

-0.67

orks

-0.67

urst

-0.66

grave

-0.66

POSITIVE LOGITS

 options

1.05

 option

0.97

finder

0.84

 Option

0.83

Option

0.81

 choices

0.81

atives

0.80

 choice

0.75

nels

0.73

 Altern

0.71

Activations Density 0.026%

mentions or instances of specific options

references to various choices or alternatives

No Comments

No Known Activations