INDEX

Explanations

verbs related to striving or aiming for a goal

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of pursuing goals or ambitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

brance

-0.76

bsite

-0.70

ritical

-0.67

âĶĢâĶĢâĶĢâĶĢ

-0.65

orah

-0.64

ombat

-0.64

imating

-0.63

js

-0.63

electric

-0.62

minus

-0.62

POSITIVE LOGITS

 avenues

0.91

 pursue

0.87

 pursued

0.85

iage

0.80

 careers

0.76

 excellence

0.76

 pursuing

0.75

 paths

0.75

ively

0.74

 objectives

0.74

Activations Density 0.030%

verbs related to striving or aiming for a goal

phrases related to the concept of pursuing goals or ambitions

No Comments

No Known Activations