INDEX

Explanations

phrases indicating a state of being in need

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a need for assistance or support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

link

-0.77

 istg

-0.71

hesis

-0.68

ula

-0.63

imilar

-0.63

opus

-0.62

nels

-0.62

mask

-0.60

must

-0.59

ucle

-0.59

POSITIVE LOGITS

 course

0.79

umbn

0.75

 sorts

0.74

ãĤ¦

0.72

 luck

0.72

 fate

0.71

 justice

0.67

 honour

0.67

ãģĤ

0.66

ãģĦ

0.65

Activations Density 0.106%

phrases indicating a state of being in need

phrases indicating a need for assistance or support

No Comments

No Known Activations