INDEX

Explanations

statements made by different individuals

oai_token-act-pair · gpt-3.5-turbo

dialogues or statements that indicate opinions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

'.

-0.86

etheless

-0.76

strate

-0.76

successfully

-0.69

 groundwork

-0.67

 conver

-0.67

conservancy

-0.65

 torch

-0.64

oint

-0.64

 knack

-0.63

POSITIVE LOGITS

Said

0.99

"],

0.85

"}

0.80

OTUS

0.75

["

0.75

="

0.75

=""

0.74

 Norn

0.73

]"

0.72

Wilson

0.72

Activations Density 1.336%

statements made by different individuals

dialogues or statements that indicate opinions or decisions

No Comments

No Known Activations