INDEX

Explanations

opinions or perspectives expressed in text

oai_token-act-pair · gpt-3.5-turbo

references to differing opinions or perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

cial

-0.73

 Mystery

-0.69

 Vigil

-0.65

breaker

-0.65

rophe

-0.64

fect

-0.64

ursed

-0.62

die

-0.62

chant

-0.62

Match

-0.61

POSITIVE LOGITS

 views

4.00

 Views

2.91

 viewpoints

2.42

views

2.33

 view

2.31

 opinions

2.13

 perspectives

1.90

 VIEW

1.82

view

1.60

 viewpoint

1.60

Activations Density 0.014%

opinions or perspectives expressed in text

references to differing opinions or perspectives

No Comments

No Known Activations