INDEX

Explanations

phrases related to value judgments or assessments

oai_token-act-pair · gpt-3.5-turbo

conjunctions, particularly the word "and" in various contexts

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

hoe

-0.73

ocular

-0.67

ursday

-0.66

emp

-0.65

igraph

-0.61

 Wheat

-0.61

orial

-0.61

 Lank

-0.60

oid

-0.60

Morning

-0.59

POSITIVE LOGITS

 THEN

0.85

 expects

0.84

 hence

0.82

 consequently

0.81

 deserve

0.80

 therefore

0.78

 hopefully

0.77

 furthermore

0.76

 then

0.76

 thus

0.76

Activations Density 0.150%

phrases related to value judgments or assessments

conjunctions, particularly the word "and" in various contexts

No Comments

No Known Activations