INDEX

Explanations

superlative descriptions or evaluations

oai_token-act-pair · gpt-3.5-turbo

terms related to significant social issues and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

tnc

-0.88

ritz

-0.82

rocal

-0.71

İĭ

-0.69

EngineDebug

-0.68

actionDate

-0.68

tiny

-0.67

 guiActiveUn

-0.67

jen

-0.65

phasis

-0.64

POSITIVE LOGITS

 imaginable

1.30

 ever

1.10

 EVER

1.10

 conceivable

0.93

ever

0.79

Ever

0.74

 Ever

0.74

 earners

0.74

 available

0.68

 feas

0.68

Activations Density 0.422%

superlative descriptions or evaluations

terms related to significant social issues and consequences

No Comments

No Known Activations