INDEX

Explanations

words related to flowing water or movement

oai_token-act-pair · gpt-3.5-turbo

references to cascading effects or sequences of events involving specific locations and individuals

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

selage

-0.90

ament

-0.85

nown

-0.82

fare

-0.77

umer

-0.76

anic

-0.76

nel

-0.75

wo

-0.74

gas

-0.74

orious

-0.73

POSITIVE LOGITS

 downhill

0.66

htt

0.65

 downgrade

0.65

zbollah

0.63

dale

0.62

ppers

0.62

 descent

0.59

TIME

0.59

dk

0.58

interstitial

0.58

Activations Density 0.044%

words related to flowing water or movement

references to cascading effects or sequences of events involving specific locations and individuals

No Comments

No Known Activations