INDEX

Explanations

prepositions relating to the position or movement between different locations

oai_token-act-pair · gpt-3.5-turbo

instances 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 @ 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

uala

-0.77

%%%%

-0.68

fficiency

-0.67

 confir

-0.67

 Canaver

-0.67

vine

-0.66

@#

-0.66

©¶æ¥µ

-0.63

notes

-0.61

afia

-0.61

POSITIVE LOGITS

 sexes

1.36

 extremes

0.92

 aforementioned

0.82

 parties

0.81

 genders

0.79

 sides

0.79

 combatants

0.77

 respective

0.77

 poles

0.77

 halves

0.76

Activations Density 0.134%

prepositions relating to the position or movement between different locations

instances of the word "the" in various contexts

No Comments

No Known Activations