INDEX

Explanations

specific words related to the act of assigning tasks or responsibilities

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "assigned" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

steen

-0.78

Ïī

-0.77

mph

-0.74

FORE

-0.73

icz

-0.71

Ste

-0.71

Stone

-0.68

razil

-0.68

OIL

-0.67

bite

-0.66

POSITIVE LOGITS

 assigned

0.91

 assign

0.84

 assigning

0.83

 assignments

0.81

otom

0.79

 assigns

0.78

 assignment

0.78

essor

0.77

nect

0.77

 allegiance

0.76

Activations Density 0.017%

specific words related to the act of assigning tasks or responsibilities

mentions of the word "assigned" and its variations

No Comments

No Known Activations