INDEX

Explanations

the word "story" at different activation levels

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "story"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

the noun "story"

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

inking

-0.93

avorite

-0.93

omin

-0.90

ignt

-0.86

omination

-0.86

elsius

-0.84

htaking

-0.81

inois

-0.81

orneys

-0.80

inence

-0.80

POSITIVE LOGITS

telling

0.93

story

0.88

arc

0.86

 revolving

0.86

 Story

0.86

 Stories

0.86

 arcs

0.85

 Reincarn

0.84

 story

0.84

boards

0.83

Activations Density 0.039%

the word "story" at different activation levels

occurrences of the word "story"

the noun "story"

No Comments

No Known Activations