INDEX

Explanations

language-related terms

oai_token-act-pair · gpt-3.5-turbo

references to language and its various forms and uses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ilon

-0.85

roxy

-0.84

ilts

-0.83

apego

-0.80

uds

-0.80

agher

-0.78

ECD

-0.77

hap

-0.76

rodu

-0.75

uden

-0.75

POSITIVE LOGITS

 language

0.96

 learners

0.94

 spoken

0.92

language

0.92

 interpreter

0.85

anguage

0.83

 immersion

0.81

 lear

0.79

 instruction

0.75

 barrier

0.75

Activations Density 0.016%

language-related terms

references to language and its various forms and uses

No Comments

No Known Activations