INDEX

Explanations

mentions of legal actions or events

oai_token-act-pair · gpt-3.5-turbo

recurring phrases that involve various contexts, particularly in legal or news-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocl

-0.85

²¾

-0.76

estones

-0.73

ideon

-0.73

istical

-0.72

ļéĨĴ

-0.68

eem

-0.68

Installation

-0.67

uten

-0.66

Newsletter

-0.66

POSITIVE LOGITS

 prompting

0.93

 citing

0.90

TMZ

0.87

aka

0.87

 according

0.85

 sparking

0.83

 CNBC

0.82

 Canaver

0.77

 amid

0.77

 forcing

0.76

Activations Density 0.380%

mentions of legal actions or events

recurring phrases that involve various contexts, particularly in legal or news-related content

No Comments

No Known Activations