INDEX

Explanations

names and words containing "er" or "es" letters with high activation

oai_token-act-pair · gpt-3.5-turbo

plural noun forms and certain suffixes that indicate various attributes

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

 EDITION

-0.64

DERR

-0.64

é¾į

-0.63

upon

-0.63

 minded

-0.62

avorite

-0.60

pants

-0.60

å§«

-0.60

 tunes

-0.59

DOWN

-0.57

POSITIVE LOGITS

ching

0.87

hiba

0.82

iency

0.82

cil

0.78

ience

0.77

idian

0.75

cher

0.73

itability

0.72

eto

0.71

isure

0.71

Activations Density 0.139%

names and words containing "er" or "es" letters with high activation

plural noun forms and certain suffixes that indicate various attributes

No Comments

No Known Activations