INDEX

Explanations

specific software, technology, and product names

oai_token-act-pair · gpt-3.5-turbo

references to specific software or technology products

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

-0.87

onies

-0.84

umbn

-0.79

/-

-0.79

akable

-0.79

aca

-0.72

ãĥ£

-0.72

lain

-0.70

mble

-0.70

uminati

-0.68

POSITIVE LOGITS

 Wire

0.79

 Ventures

0.79

 Accessories

0.79

 Launch

0.76

 itself

0.74

 Defender

0.73

 Composite

0.73

 Wireless

0.73

Corp

0.72

 Logic

0.72

Activations Density 0.266%

specific software, technology, and product names

references to specific software or technology products

No Comments

No Known Activations