INDEX

Explanations

words related to obstacles or hindrances in different contexts

oai_token-act-pair · gpt-3.5-turbo

terms associated with obstacles and difficulties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ISTORY

-0.77

vironment

-0.74

lique

-0.72

racuse

-0.71

ITNESS

-0.69

ndra

-0.68

irtual

-0.65

naissance

-0.64

alt

-0.64

ultane

-0.64

POSITIVE LOGITS

luster

0.78

 barriers

0.69

nesses

0.67

 Nadu

0.66

 havoc

0.64

 hamstring

0.63

 undermin

0.62

 mobility

0.62

backs

0.62

rance

0.62

Activations Density 0.159%

words related to obstacles or hindrances in different contexts

terms associated with obstacles and difficulties

No Comments

No Known Activations