INDEX

Explanations

mentions of atomic-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to atomic energy and nuclear events

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

 Fargo

-0.94

atche

-0.80

cific

-0.76

shire

-0.75

nir

-0.74

Guard

-0.65

sburgh

-0.64

anson

-0.64

llers

-0.63

PE

-0.63

POSITIVE LOGITS

ysis

0.89

 atoms

0.89

 atom

0.88

 nucle

0.88

atomic

0.87

 atomic

0.85

omach

0.82

atom

0.81

 nucleus

0.80

 latt

0.80

Activations Density 0.039%

mentions of atomic-related terms

terms related to atomic energy and nuclear events

No Comments

No Known Activations