INDEX

Explanations

words related to goals or intended outcomes

oai_token-act-pair · gpt-3.5-turbo

instances of the term "objective" and related concepts

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

oles

-0.85

artifacts

-0.77

sing

-0.73

aps

-0.72

jen

-0.71

 Tycoon

-0.70

ocket

-0.69

paces

-0.69

ingers

-0.68

Lago

-0.68

POSITIVE LOGITS

 objective

1.07

 Objective

1.05

 observer

0.83

ives

0.81

 goal

0.80

 objectives

0.80

ignty

0.78

 guiActiveUn

0.73

ablishment

0.73

isable

0.69

Activations Density 0.010%

words related to goals or intended outcomes

instances of the term "objective" and related concepts

No Comments

No Known Activations