INDEX

Explanations

references to conflicts of interest

oai_token-act-pair · gpt-3.5-turbo

references to conflicts of interest

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

LESS

-0.64

jog

-0.63

Die

-0.62

Die

-0.61

Drag

-0.61

 starve

-0.60

hound

-0.60

 Unch

-0.59

hunt

-0.59

 Dodge

-0.58

POSITIVE LOGITS

 interests

0.93

 interest

0.87

 Interest

0.83

ategory

0.76

Interest

0.75

interest

0.75

ortunately

0.71

rontal

0.69

 tradem

0.68

artment

0.68

Activations Density 0.083%

references to conflicts of interest

references to conflicts of interest

No Comments

No Known Activations