INDEX

Explanations

references to or mentions of icons

oai_token-act-pair · gpt-3.5-turbo

references to icons or symbolic representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

EEE

-0.68

ingly

-0.67

ndum

-0.65

THER

-0.65

UGE

-0.64

nda

-0.62

 Thoughts

-0.62

IGH

-0.62

razil

-0.60

OUT

-0.59

POSITIVE LOGITS

ocl

1.53

ically

1.19

nect

1.07

icity

1.02

ographically

1.00

ography

0.99

icons

0.93

ographic

0.92

ico

0.91

icon

0.90

Activations Density 0.032%

references to or mentions of icons

references to icons or symbolic representations

No Comments

No Known Activations