INDEX

Explanations

proper nouns, specifically the name "Andre"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Andre" in various contexts

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

inct

-0.72

ointed

-0.69

ulhu

-0.64

eled

-0.64

clips

-0.61

elled

-0.61

stellar

-0.61

dfx

-0.60

ellen

-0.59

stakes

-0.58

POSITIVE LOGITS

tti

1.16

essen

1.05

byss

0.92

cats

0.78

 Drum

0.74

gie

0.72

iev

0.71

Vu

0.69

 Damon

0.69

Activations Density 0.026%

proper nouns, specifically the name "Andre"

occurrences of the name "Andre" in various contexts

No Comments

No Known Activations