INDEX

Explanations

phrases related to physical actions or events

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation and certain significant phrases

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

usterity

-0.76

orer

-0.72

zbek

-0.66

OND

-0.66

aran

-0.66

obin

-0.64

NK

-0.63

TN

-0.61

nai

-0.61

ctor

-0.60

POSITIVE LOGITS

}"

0.67

FontSize

0.66

 respectively

0.60

0.59

 Minotaur

0.58

 decap

0.58

peg

0.57

 diminishing

0.57

viz

0.57

rained

0.56

Activations Density 0.287%

phrases related to physical actions or events

instances of punctuation and certain significant phrases

No Comments

No Known Activations