INDEX

Explanations

generic verbs related to assigning or designating

oai_token-act-pair · gpt-3.5-turbo

instances 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bite

-0.75

icz

-0.73

steen

-0.72

DOC

-0.72

Ïī

-0.71

psc

-0.69

razil

-0.68

FORE

-0.67

apest

-0.67

EH

-0.66

POSITIVE LOGITS

 assignment

0.86

 assign

0.83

 assigned

0.83

 assignments

0.82

 allegiance

0.82

 assigns

0.81

otom

0.79

 assigning

0.78

istant

0.77

esthetic

0.74

Activations Density 0.031%

generic verbs related to assigning or designating

instances of the word "assigned" and its variations

No Comments

No Known Activations