INDEX

Explanations

phrases related to presenting information or reports

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to presenting or showcasing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffff

-0.87

ï¸ı

-0.85

terness

-0.79

ache

-0.74

kie

-0.70

recy

-0.67

 tweeting

-0.66

icka

-0.65

ionage

-0.63

POSITIVE LOGITS

 evidence

0.88

 slides

0.83

 Exhibit

0.80

 presentations

0.79

 hypotheses

0.76

 alternatives

0.75

evidence

0.75

 arguments

0.73

 PowerPoint

0.72

 presented

0.72

Activations Density 0.079%

phrases related to presenting information or reports

words and phrases related to presenting or showcasing information

No Comments

No Known Activations