INDEX

Explanations

phrases indicating a position of being behind or falling behind in a competition or comparison

oai_token-act-pair · gpt-3.5-turbo

instances of the word "behind" in varying 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

oret

-0.75

Pwr

-0.73

enegger

-0.70

isms

-0.65

vic

-0.64

eri

-0.64

owe

-0.64

elf

-0.64

istic

-0.64

escal

-0.62

POSITIVE LOGITS

ienced

0.81

shore

0.76

 schedule

0.70

âĸ¬âĸ¬

0.69

coat

0.66

beat

0.66

 bars

0.64

stood

0.64

oos

0.62

roups

0.61

Activations Density 0.016%

phrases indicating a position of being behind or falling behind in a competition or comparison

instances of the word "behind" in varying contexts

No Comments

No Known Activations