INDEX

Explanations

phrases related to specific locations or activities within a location

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" in various contexts

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

pers

-0.85

SPONSORED

-0.82

strap

-0.75

fulness

-0.74

udder

-0.71

arians

-0.69

 namely

-0.69

cules

-0.68

Ïĥ

-0.68

 onwards

-0.67

POSITIVE LOGITS

 same

1.04

 forefront

1.02

 midst

1.02

 doorway

0.97

 proverbial

0.94

 closet

0.93

 halls

0.91

 streets

0.88

 confines

0.88

 kitchen

0.85

Activations Density 0.606%

phrases related to specific locations or activities within a location

occurrences of the word "the" in various contexts

No Comments

No Known Activations