INDEX

Explanations

specific instances of the word "the"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

bg

-0.82

Ò

-0.79

 thereby

-0.76

thood

-0.74

tec

-0.73

ceive

-0.71

arate

-0.71

pection

-0.70

cpu

-0.69

visory

-0.69

POSITIVE LOGITS

oret

1.23

 biggest

1.11

 simplest

1.10

resa

1.08

 slightest

1.08

 greatest

1.06

 sheer

1.06

 easiest

1.05

 smartest

1.04

 notion

1.04

Activations Density 0.621%

specific instances of the word "the"

occurrences of the word "the."

No Comments

No Known Activations