INDEX

Explanations

phrases indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" and its contextual significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

indal

-0.88

skirts

-0.88

FTWARE

-0.78

mber

-0.77

duction

-0.74

igers

-0.72

ptives

-0.71

APTER

-0.69

lees

-0.68

iris

-0.68

POSITIVE LOGITS

 paraph

0.84

 essence

0.74

 guessed

0.72

 paradox

0.72

 quote

0.71

 aggregate

0.68

 plaus

0.68

 surprisingly

0.67

 incidentally

0.67

 probability

0.66

Activations Density 0.125%

phrases indicating emphasis or importance

the preposition "in" and its contextual significance

No Comments

No Known Activations