INDEX

Explanations

phrases or sentences referencing narratives or personal accounts

oai_token-act-pair · gpt-3.5-turbo

references to storytelling

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

orneys

-0.94

ategory

-0.80

utterstock

-0.79

ateurs

-0.78

tarian

-0.77

owler

-0.77

ignt

-0.77

inking

-0.75

ojure

-0.75

upiter

-0.74

POSITIVE LOGITS

telling

0.98

 tale

0.91

arc

0.88

 tales

0.85

tale

0.85

 arcs

0.85

 Tales

0.82

 unfolding

0.81

 Stories

0.80

 stories

0.78

Activations Density 0.042%

phrases or sentences referencing narratives or personal accounts

references to storytelling

No Comments

No Known Activations