INDEX

Explanations

descriptive adjectives describing the pace, structure, and style of writing

oai_token-act-pair · gpt-3.5-turbo

critical assessments of artistic works

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

 Government

-0.75

 expired

-0.73

IFIED

-0.72

ospons

-0.72

Federal

-0.71

 certified

-0.71

 Certification

-0.70

 credential

-0.70

 certification

-0.69

 reimbursement

-0.69

POSITIVE LOGITS

 cinematic

1.13

 tropes

1.09

 Lovecraft

1.08

 ensemble

1.05

 narration

1.03

 Whedon

1.00

 genre

0.97

 soundtrack

0.97

 Godzilla

0.95

 climax

0.94

Activations Density 1.449%

descriptive adjectives describing the pace, structure, and style of writing

critical assessments of artistic works

No Comments

No Known Activations