INDEX

Explanations

instances of specific locations or directions in a driving context

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating location or spatial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

TPP

-0.83

INESS

-0.75

AMA

-0.71

rament

-0.69

RL

-0.67

APP

-0.67

Except

-0.66

Protect

-0.66

Parser

-0.65

Mini

-0.65

POSITIVE LOGITS

 behalf

1.40

etime

1.21

yx

1.06

shore

1.05

coming

1.05

 occasion

1.01

 patrol

0.93

 rooft

0.93

site

0.91

 arrival

0.90

Activations Density 0.265%

instances of specific locations or directions in a driving context

prepositions indicating location or spatial relationships

No Comments

No Known Activations