INDEX

Explanations

names related to headwear, specifically focusing on the term "hat"

oai_token-act-pair · gpt-3.5-turbo

words related to various "Hat" terms and brands

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

ngth

-1.11

theless

-0.97

 glutamate

-0.82

naire

-0.76

¥ŀ

-0.70

hower

-0.69

Õ

-0.68

taining

-0.67

è»

-0.65

selves

-0.64

POSITIVE LOGITS

chery

1.04

chet

1.02

ches

0.87

wig

0.82

ched

0.78

mut

0.78

cher

0.78

Hat

0.77

stack

0.76

red

0.76

Activations Density 0.011%

names related to headwear, specifically focusing on the term "hat"

words related to various "Hat" terms and brands

No Comments

No Known Activations