INDEX

Explanations

phrases indicating a presentation or introduction of information

oai_token-act-pair · gpt-3.5-turbo

instances of acknowledgment or recognition of knowledge

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ella

-0.74

emon

-0.65

ocide

-0.64

nai

-0.62

ÃŃa

-0.61

etermined

-0.61

 physic

-0.60

 realism

-0.60

absolute

-0.60

 Ambro

-0.59

POSITIVE LOGITS

 WATCHED

0.77

 yourselves

0.75

>:

0.74

BAT

0.69

 Pastebin

0.68

ptives

0.67

ACTED

0.67

 Lank

0.65

hin

0.65

tale

0.64

Activations Density 0.287%

phrases indicating a presentation or introduction of information

instances of acknowledgment or recognition of knowledge

No Comments

No Known Activations