INDEX

Explanations

legal and regulatory terms and abbreviations

oai_token-act-pair · gpt-3.5-turbo

sentence-like structures or punctuation marks indicating finality

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

 Seth

-0.74

krit

-0.72

 frontline

-0.69

ensical

-0.68

nesday

-0.68

 nightly

-0.67

 shores

-0.65

 everywhere

-0.65

ĸļ

-0.63

 painting

-0.63

POSITIVE LOGITS

Example

1.21

Definition

1.15

âĵĺ

1.12

Returns

1.09

Methods

1.08

References

1.08

Examples

1.06

Trivia

1.05

Effective

1.04

NOTE

1.04

Activations Density 0.314%

legal and regulatory terms and abbreviations

sentence-like structures or punctuation marks indicating finality

No Comments

No Known Activations