INDEX

Explanations

phrases indicating a specific situation or scenario

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to the concept of "case" or situations being discussed

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

airs

-0.82

sg

-0.73

etsk

-0.73

icket

-0.69

srf

-0.67

slow

-0.67

grave

-0.67

 livest

-0.66

nesday

-0.66

egu

-0.66

POSITIVE LOGITS

 Canaver

0.87

cases

0.87

Ruk

0.79

 Levine

0.76

 exception

0.75

liest

0.74

 Heller

0.71

 Keen

0.71

igraph

0.71

 Maher

0.70

Activations Density 0.019%

phrases indicating a specific situation or scenario

phrases that refer to the concept of "case" or situations being discussed

No Comments

No Known Activations